© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 32083
    Prev
    Next
    INDEX
    Explanations

    internal self and others

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

    inner self / consciousness

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    زندگی
    0.46
     decorate
    0.46
    社会的
    0.45
    橢
    0.45
    InterfaceLine
    0.44
    ین
    0.43
    جاد
    0.42
    Merr
    0.42
    ز
    0.41
    ल
    0.41
    POSITIVE LOGITS
     നിന്ന്
    0.48
     veine
    0.46
     cavité
    0.45
     indel
    0.43
     instilled
    0.42
    tiket
    0.41
     veines
    0.41
     conscience
    0.41
    徹底
    0.41
     firmly
    0.40
    Activations Density 0.048%

    No Known Activations