© 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. 238213
    Prev
    Next
    INDEX
    Explanations

    grammar definition, August, claw tires, block chain, intolerant

    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
    मीत
    0.41
    Fleet
    0.41
    θη
    0.41
    嵐
    0.40
    閒
    0.40
    粨
    0.40
     склады
    0.40
    潛
    0.40
    መሳ
    0.39
     sobra
    0.39
    POSITIVE LOGITS
     disintegrated
    0.47
     sinned
    0.46
     gripped
    0.46
     проще
    0.45
    uts
    0.44
     tabled
    0.44
    q
    0.44
     äh
    0.43
    uming
    0.42
     whack
    0.42
    Activations Density 0.000%

    No Known Activations