© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 146312
    Prev
    Next
    INDEX
    Explanations

    waterproof iPhone, vote March

    np_acts-logits-general · gemini-2.5-flash-lite

    Salt, Specification, Protection

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    imizi
    0.54
     mouseDown
    0.51
    imize
    0.51
     m
    0.49
     contingent
    0.46
     profiling
    0.46
     PL
    0.45
     NA
    0.45
     contoured
    0.45
    waitFor
    0.45
    POSITIVE LOGITS
    别墅
    0.54
    关键字
    0.50
    之类的
    0.49
    RoleId
    0.49
    伈
    0.49
    半径
    0.49
    鸠
    0.48
    Hierarchy
    0.48
     அவ
    0.48
    选中
    0.47
    Activations Density 0.001%

    No Known Activations