© 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. 128067
    Prev
    Next
    INDEX
    Explanations

    wind chimes for funeral

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

    movie, existing, previously

    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
    趄
    0.46
     kalian
    0.44
    će
    0.43
    communicate
    0.42
    candidates
    0.41
     توهان
    0.41
     će
    0.40
    чыць
    0.40
     تعالى
    0.40
     berita
    0.40
    POSITIVE LOGITS
    пан
    0.46
     অবস্থায়
    0.45
    ▸
    0.45
     ILLINOIS
    0.44
    avais
    0.44
    꽈
    0.44
    пень
    0.43
    壮
    0.43
    욬
    0.43
    었
    0.42
    Activations Density 0.000%

    No Known Activations