© 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. 9465
    Prev
    Next
    INDEX
    Explanations

    在家, 馆, 里的

    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
    選手
    0.48
    節
    0.48
    <unused1882>
    0.45
    釗
    0.45
    思議
    0.44
    蛲
    0.44
    娠
    0.44
    僑
    0.43
     선수
    0.42
    應用
    0.42
    POSITIVE LOGITS
     long
    0.46
     dos
    0.44
     are
    0.43
     go
    0.43
     stares
    0.43
     take
    0.43
     cost
    0.43
    里
    0.42
     para
    0.41
    里的
    0.41
    Activations Density 0.000%

    No Known Activations