© 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. 165159
    Prev
    Next
    INDEX
    Explanations

    numbers and punctuation

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

    SMS table operations

    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
     Soll
    0.45
     ডকুমেন্ট
    0.43
    𒐪
    0.42
    ترض
    0.42
     Corb
    0.41
    جه
    0.40
    🇧
    0.40
     Gutiérrez
    0.40
    ंतु
    0.40
     Colle
    0.40
    POSITIVE LOGITS
    string
    0.42
     automat
    0.39
     秋
    0.39
     decidir
    0.38
    nod
    0.38
    finally
    0.38
    series
    0.38
     permitem
    0.37
    countdown
    0.37
     finalmente
    0.37
    Activations Density 0.000%

    No Known Activations