© 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. 121275
    Prev
    Next
    INDEX
    Explanations

    topics and concepts

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

    definitions and technical terms

    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
     clamped
    0.45
    тім
    0.44
     melap
    0.43
     này
    0.43
     koń
    0.43
    ў
    0.42
     rag
    0.42
     och
    0.41
    این
    0.41
     rite
    0.41
    POSITIVE LOGITS
    エントリー
    0.55
     kategorie
    0.51
     ويكي
    0.49
     جري
    0.47
    LOLLIPOP
    0.46
    샛
    0.46
    िडेट
    0.46
     rookies
    0.45
     Idol
    0.44
    idE
    0.44
    Activations Density 0.001%

    No Known Activations