© 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. 217518
    Prev
    Next
    INDEX
    Explanations

    terms and conditions

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

    answering questions

    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
    едера
    0.49
    рур
    0.44
     Fraction
    0.43
    uración
    0.42
    aría
    0.40
    риди
    0.40
    姹
    0.40
    дження
    0.40
    }),
    0.39
    ematic
    0.39
    POSITIVE LOGITS
     نویس
    0.57
    ks
    0.52
     بال
    0.50
     كتب
    0.50
     እንቅ
    0.49
    ts
    0.49
    cub
    0.48
    führer
    0.48
    ClearedBy
    0.48
     الق
    0.47
    Activations Density 0.000%

    No Known Activations