© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 102997
    Prev
    Next
    INDEX
    Explanations

    you are adjectives or nouns

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

    The neuron fires on direct second-person compliments or praise (e.g. “You are a star,” “You’re amazing,” etc.).

    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
     is
    -1.29
     isn
    -1.22
     heerlijk
    -1.21
     your
    -1.20
     Doesn
    -1.19
     already
    -1.16
    iconos
    -1.15
     doesn
    -1.14
     garrafa
    -1.12
    вы
    -1.11
    POSITIVE LOGITS
    }
    1.35
    ранже
    1.30
    infeld
    1.23
    庭園
    1.18
     fundamenta
    1.15
    ñera
    1.13
     отца
    1.11
     Verlauf
    1.11
    efforts
    1.11
     narra
    1.09
    Activations Density 0.048%

    No Known Activations