© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 139116
    Prev
    Next
    INDEX
    Explanations

    avoiding harmful content

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     студен
    0.46
    课堂
    0.46
    祸
    0.46
    学生
    0.45
    DeathRecord
    0.44
    显示的
    0.44
     单
    0.43
    象征
    0.43
    FBSDKSettings
    0.43
     документа
    0.41
    POSITIVE LOGITS
    소를
    0.54
    尷
    0.46
     améliorer
    0.45
    當年
    0.44
     marav
    0.43
    整備
    0.42
     crescimento
    0.42
     marina
    0.41
     améli
    0.41
     verbessern
    0.41
    Activations Density 0.007%

    No Known Activations