© 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. 104366
    Prev
    Next
    INDEX
    Explanations

    cause and effect

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

    cause and effect

    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
     да
    0.49
     configuring
    0.48
     وی
    0.47
     ли
    0.47
     microfiber
    0.46
     σύ
    0.46
     دھ
    0.46
    脏
    0.46
    咦
    0.46
     зах
    0.45
    POSITIVE LOGITS
    event
    0.46
     tanggung
    0.46
    イベント
    0.44
    तोंडा
    0.43
    uterine
    0.43
     Gilbert
    0.42
     Ereign
    0.42
    חו
    0.42
     Viktor
    0.42
     ഉത്തര
    0.42
    Activations Density 0.000%

    No Known Activations