© 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. 22462
    Prev
    Next
    INDEX
    Explanations

    septic, Blendetto, address components

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

    abstract scenarios and potential actions

    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
     多く
    0.57
     บท
    0.46
    这话
    0.46
    ^{
    0.43
    外的
    0.41
     うん
    0.39
    เอง
    0.38
    多く
    0.38
     フレ
    0.38
    片段
    0.38
    POSITIVE LOGITS
    기
    0.50
     mosques
    0.50
     keyring
    0.49
     memungkinkan
    0.48
     funcionarios
    0.48
     proveedor
    0.48
     تجهیز
    0.47
     incluida
    0.47
     thermocou
    0.47
     motorway
    0.46
    Activations Density 0.000%

    No Known Activations