© 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. 52141
    Prev
    Next
    INDEX
    Explanations

    said, set, in, the

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

    museum names

    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
     Sturm
    0.56
     Speak
    0.54
     speak
    0.53
     কারও
    0.52
     대체
    0.50
     방법을
    0.50
     Uma
    0.49
    赡
    0.49
     벡터
    0.49
     species
    0.49
    POSITIVE LOGITS
    in
    0.55
    incre
    0.49
    toggler
    0.47
    BusinessType
    0.47
    यों
    0.46
    RETURNS
    0.45
    roo
    0.45
    badge
    0.44
    returns
    0.44
    constraintlayout
    0.44
    Activations Density 0.000%

    No Known Activations