© 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. 159311
    Prev
    Next
    INDEX
    Explanations

    child guest charge

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

    started demonstration

    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
    নি
    0.53
    曈
    0.51
     geplant
    0.50
    悆
    0.50
    ים
    0.49
    档案馆
    0.48
    Medic
    0.48
     Urgent
    0.47
    ূতন
    0.47
     Planung
    0.47
    POSITIVE LOGITS
    cod
    0.52
    c
    0.50
    cub
    0.47
    inder
    0.45
    mc
    0.45
    cü
    0.45
    istream
    0.45
    gi
    0.45
     testo
    0.42
     متن
    0.42
    Activations Density 0.000%

    No Known Activations