© 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. 210544
    Prev
    Next
    INDEX
    Explanations

    numbers and units

    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
    ],//
    0.39
     linear
    0.38
     skeletons
    0.37
     Moc
    0.37
    ">—
    0.37
     ado
    0.36
     ts
    0.36
    ,/*
    0.36
     পি
    0.35
     clamp
    0.35
    POSITIVE LOGITS
    leva
    0.47
    鸣
    0.43
    ственно
    0.42
    哃
    0.41
    lech
    0.40
    ledi
    0.40
    ǎi
    0.40
    WindowConstants
    0.39
    ơi
    0.39
    ssid
    0.39
    Activations Density 0.011%

    No Known Activations