© 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. 43607
    Prev
    Next
    INDEX
    Explanations

    hired actors, tote bags, boat

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

    foreign language or script

    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
     Analyse
    0.54
     To
    0.47
     consul
    0.46
     onto
    0.45
     (<
    0.45
     Advice
    0.45
     wyniku
    0.45
    ers
    0.45
     Of
    0.44
    者的
    0.44
    POSITIVE LOGITS
    ಟ್ರ
    0.56
     うる
    0.52
    がつ
    0.51
     ビタミン
    0.49
     алюми
    0.49
     ಗೋ
    0.49
    measuredangle
    0.48
     ιστο
    0.48
    niOkno
    0.48
    莧
    0.47
    Activations Density 0.000%

    No Known Activations