© 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. 51808
    Prev
    Next
    INDEX
    Explanations

    party buses or tile cleaning

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

    medical or sexual terms

    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
    ریل
    0.55
    ری
    0.53
    گ
    0.52
     putern
    0.51
     sobre
    0.47
    зі
    0.47
    าล
    0.47
    ل
    0.47
     obtenidos
    0.46
    ੀ
    0.46
    POSITIVE LOGITS
     creeks
    0.53
    fonos
    0.48
     六
    0.46
     ];
    0.45
     至
    0.45
    市区
    0.44
     遅く
    0.44
    ండ్
    0.44
     каттоосуз
    0.43
     Creek
    0.42
    Activations Density 0.000%

    No Known Activations