© 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. 112892
    Prev
    Next
    INDEX
    Explanations

    languages other than English publications

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

    scripting and copying data

    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
    itions
    0.49
    ilities
    0.42
    fifths
    0.41
    通勤
    0.41
    efficients
    0.40
     mitad
    0.40
     والمر
    0.40
    癞
    0.40
     fases
    0.40
    مي
    0.40
    POSITIVE LOGITS
     verfügbar
    0.50
    เมื่อ
    0.46
     जवळ
    0.45
     शुभारंभ
    0.45
     మేము
    0.45
    มอบ
    0.45
    usega
    0.43
     ज्ञापन
    0.42
     স্মরণ
    0.42
     A
    0.42
    Activations Density 0.003%

    No Known Activations