© 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. 219760
    Prev
    Next
    INDEX
    Explanations

    will post update

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

    Storage requirements and technical terms

    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
     Москвы
    0.54
    服用
    0.47
    路線
    0.43
     participaron
    0.42
    丢失
    0.41
    協助
    0.41
    鐳
    0.40
     asistir
    0.40
    服
    0.40
     निम्न
    0.40
    POSITIVE LOGITS
    keun
    0.50
    𝕝
    0.49
    😄
    0.47
    ק
    0.46
     psychopath
    0.45
    ~$
    0.45
     Rohing
    0.44
    larından
    0.44
    ไ
    0.44
    OOOO
    0.43
    Activations Density 0.012%

    No Known Activations