© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 10487
    Prev
    Next
    INDEX
    Explanations

    my code I wanted

    np_acts-logits-general · gemini-2.5-flash-lite

    first-person pronouns followed by past tense verbs describing personal actions or experiences.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    This neuron detects first-person narrative phrasing, especially the pronoun “I” and its associated personal actions or statements.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     of
    -1.87
     a
    -1.74
     its
    -1.66
     like
    -1.54
     who
    -1.43
     his
    -1.33
     pilares
    -1.30
     geweldig
    -1.26
    çou
    -1.22
     verdaderos
    -1.21
    POSITIVE LOGITS
    先日
    1.30
     одним
    1.23
    ной
    1.14
    どうも
    1.12
     InputMaybe
    1.11
     откры
    1.09
    Not
    1.05
    AÇÃO
    1.05
    無論
    1.04
    ční
    1.02
    Activations Density 0.108%

    No Known Activations