© 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. 7586
    Prev
    Next
    INDEX
    Explanations

    scoring or points

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

    question number

    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
     Addition
    0.37
     arriva
    0.36
     Achievement
    0.36
     diventa
    0.36
     লিস্ট
    0.36
     solns
    0.35
    Ꮫ
    0.35
     Pendant
    0.35
     Flicker
    0.35
    टेट
    0.35
    POSITIVE LOGITS
    ~\
    0.46
    行動
    0.45
    ^{+}(
    0.43
    共产
    0.43
    （
    0.41
     (\
    0.40
     هفت
    0.40
    🛂
    0.40
    一方面
    0.40
    🈚
    0.39
    Activations Density 0.000%

    No Known Activations