© 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. 143872
    Prev
    Next
    INDEX
    Explanations

    encourage, limit, support, starve

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

    causes effects and results

    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
    變得
    0.42
    剡
    0.40
    燊
    0.39
    카오
    0.39
    減少
    0.38
     Shock
    0.37
    ካት
    0.37
     Sunshine
    0.36
     currentWeather
    0.36
     সার্টিফি
    0.36
    POSITIVE LOGITS
     inducement
    0.44
    incent
    0.43
     الطب
    0.40
     favor
    0.38
    孵
    0.37
     incentive
    0.37
     Fuerza
    0.36
    ፈር
    0.36
    眶
    0.36
    undai
    0.36
    Activations Density 0.089%

    No Known Activations