© 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. 51996
    Prev
    Next
    INDEX
    Explanations

    acronyms or initialisms

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

    full-fat recommended

    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
     Ayer
    0.50
     Hickey
    0.48
     ટીમ
    0.46
     Prima
    0.45
     টিম
    0.45
    🅘
    0.45
     unprofessional
    0.44
     Bilbao
    0.44
     Greenberg
    0.44
    getTeam
    0.44
    POSITIVE LOGITS
     weights
    0.48
    ﺟ
    0.46
    Introduction
    0.46
     bands
    0.45
    QUOTE
    0.44
    אנ
    0.43
     sparks
    0.42
    Veget
    0.42
     commands
    0.42
     salts
    0.42
    Activations Density 0.000%

    No Known Activations