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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 33785
    Prev
    Next
    INDEX
    Explanations

    states of being

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

    The neuron flags emotionally intense or dramatic language—words and punctuation conveying strong feelings or emphasis.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    ;<
    -1.16
     pernic
    -1.14
    intended
    -1.13
     robuste
    -1.12
     ideale
    -1.11
    rifying
    -1.05
     devast
    -1.04
     douane
    -1.04
     vété
    -1.03
     élev
    -1.02
    POSITIVE LOGITS
     ready
    1.40
     unable
    1.38
     involved
    1.23
     have
    1.20
     prone
    1.18
     angry
    1.16
     able
    1.15
     alone
    1.11
     anxious
    1.09
     out
    1.09
    Activations Density 0.049%

    No Known Activations