© 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. 220338
    Prev
    Next
    INDEX
    Explanations

    phrases commonly appearing together

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

    discrepancy in Chapters

    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
     چھ
    0.51
     ヒ
    0.51
     ユ
    0.50
     procesamiento
    0.46
     彼
    0.46
    明白
    0.45
     များ
    0.45
    幼稚園
    0.45
     ذلك
    0.45
    ΗΣ
    0.45
    POSITIVE LOGITS
    s
    0.56
    San
    0.53
    sor
    0.50
    선
    0.48
     San
    0.47
    son
    0.46
    tion
    0.46
     Juris
    0.46
    t
    0.46
    lon
    0.45
    Activations Density 0.000%

    No Known Activations