© 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. 113134
    Prev
    Next
    INDEX
    Explanations

    destructive parameters

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

    prime factorization and remains

    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
     μεγαλ
    0.52
    憲
    0.47
     Formatting
    0.43
    getFocus
    0.42
    Illuminate
    0.42
     nineties
    0.42
    AddField
    0.42
    ắc
    0.41
    群体
    0.41
    orne
    0.41
    POSITIVE LOGITS
     RIC
    0.51
    t
    0.50
    _
    0.50
     CRUZ
    0.50
    WERS
    0.50
    ت
    0.49
     Tets
    0.49
     CHRIST
    0.48
    OSITION
    0.48
     pillows
    0.47
    Activations Density 0.001%

    No Known Activations