© 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. 204987
    Prev
    Next
    INDEX
    Explanations

    control reactions or representation

    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
    ותר
    0.40
    arak
    0.39
     }-\
    0.38
    peg
    0.37
    arbeiten
    0.37
    PEG
    0.36
     Hartree
    0.36
    颗粒
    0.36
    腆
    0.35
    etal
    0.35
    POSITIVE LOGITS
     カップ
    0.39
    ())));
    0.38
    FocusValue
    0.37
    Bind
    0.36
     Pilots
    0.36
     року
    0.36
     consciously
    0.36
    CZ
    0.36
     Summon
    0.35
    шк
    0.35
    Activations Density 0.000%

    No Known Activations