© 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
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 6610
    Prev
    Next
    INDEX
    Explanations

    AMS, amxmodx, latex

    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_40_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
    वानगी
    0.49
    ভোকেট
    0.45
    밂
    0.42
     sedative
    0.41
    逞
    0.40
    GUNDABAD
    0.40
    eteries
    0.40
    }^{-}\
    0.39
    サスカ
    0.39
     сильно
    0.39
    POSITIVE LOGITS
     AMS
    0.45
    el
    0.43
    am
    0.43
     Am
    0.42
    1
    0.42
    0.42
    Am
    0.41
     am
    0.40
    Ext
    0.40
    B
    0.39
    Activations Density 0.000%

    No Known Activations