© 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. 137312
    Prev
    Next
    INDEX
    Explanations

    finger lightly

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

    verbs and states

    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
    鞄
    0.48
    WHO
    0.44
    洏
    0.43
     Containing
    0.43
     אחר
    0.42
     resultante
    0.42
     importa
    0.42
    SELECT
    0.41
     يؤ
    0.41
     toplum
    0.41
    POSITIVE LOGITS
    ู
    0.57
    ப்பின்
    0.48
    ਿਲ
    0.46
    瑛
    0.46
     giov
    0.45
     curry
    0.45
    oge
    0.45
    ঘাতে
    0.45
    ポーツ
    0.44
    mont
    0.44
    Activations Density 0.000%

    No Known Activations