© 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. 110871
    Prev
    Next
    INDEX
    Explanations

    academic and research fields

    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
    vad
    0.37
    enic
    0.37
     feast
    0.36
    载
    0.35
    rean
    0.33
     Par
    0.33
    getParent
    0.33
    joon
    0.33
    earic
    0.33
     particip
    0.32
    POSITIVE LOGITS
     brazil
    0.48
     brazilian
    0.47
    qualiter
    0.46
    产
    0.45
    HOOK
    0.42
    logne
    0.42
    call
    0.41
     prodotti
    0.41
     Brésil
    0.41
     роз
    0.41
    Activations Density 0.003%

    No Known Activations