© 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. 247634
    Prev
    Next
    INDEX
    Explanations

    specific phrases and clauses

    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
     aides
    0.51
    agreement
    0.49
     couches
    0.48
    ه
    0.48
    وسي
    0.48
    ーズ
    0.46
    火箭
    0.46
    ربون
    0.45
    ΡΟ
    0.45
    ार्ड
    0.45
    POSITIVE LOGITS
     Pandemic
    0.44
     วิชา
    0.42
     ey
    0.42
     Eval
    0.41
     গ্রন্থ
    0.41
    丰富
    0.41
    缤
    0.41
    মুখী
    0.40
     konsult
    0.40
     bestseller
    0.40
    Activations Density 0.000%

    No Known Activations