© 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. 218607
    Prev
    Next
    INDEX
    Explanations

    ml Blogger locks

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

    complex mechanism

    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
    KK
    0.46
    翻译
    0.46
    推送
    0.46
    德
    0.45
    行星
    0.43
    បែ
    0.43
     trotzdem
    0.43
    视觉
    0.43
     düz
    0.42
    导
    0.42
    POSITIVE LOGITS
     関係
    0.54
    サイクル
    0.49
     バイ
    0.49
    inati
    0.48
     неда
    0.48
     thèse
    0.48
     効果
    0.48
     સંખ્યા
    0.47
    쵝
    0.47
    追い
    0.46
    Activations Density 0.000%

    No Known Activations