© 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. 133879
    Prev
    Next
    INDEX
    Explanations

    preceding contextual words

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

    personal, managing, jasmine, Leo

    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
    开始了
    0.42
     Encyclopædia
    0.41
    ---
    0.40
     Nationalism
    0.40
     altına
    0.39
     Italian
    0.39
    বেশ
    0.39
     অঙ্গ
    0.38
    离开了
    0.38
     Enough
    0.38
    POSITIVE LOGITS
    listar
    0.49
    キラ
    0.49
     meglio
    0.48
    님이
    0.48
    님
    0.48
     школова
    0.47
     estarán
    0.46
    kog
    0.46
     herman
    0.46
    ଃ
    0.46
    Activations Density 0.001%

    No Known Activations