© 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. 105079
    Prev
    Next
    INDEX
    Explanations

    craps, nadex, copy with, provider, Canvas Guide

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

    direct materials, both sides, relevant parts

    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
    a
    0.63
    code
    0.54
    collision
    0.51
    projects
    0.47
    aj
    0.47
    foundation
    0.46
    motivation
    0.46
    }")
    0.45
     smiles
    0.45
    parametri
    0.45
    POSITIVE LOGITS
     эле
    0.47
     neumáticos
    0.46
    LinkLabel
    0.45
     રહ્યો
    0.44
    ですか
    0.42
     lichaam
    0.42
    Verifier
    0.42
    ujesz
    0.42
    VerFile
    0.42
    ercus
    0.42
    Activations Density 0.001%

    No Known Activations