© 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. 248252
    Prev
    Next
    INDEX
    Explanations

    vocabulary and related concepts

    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
    thumbnail
    0.54
    k
    0.50
    this
    0.50
    áz
    0.48
    бо
    0.47
    thank
    0.47
    playerId
    0.46
     régl
    0.46
    du
    0.46
    ဤ
    0.46
    POSITIVE LOGITS
     kosakata
    0.65
     fluidity
    0.50
     ので
    0.50
    >∈</
    0.50
     vocabulary
    0.49
     diffusivity
    0.49
     konte
    0.48
    玤
    0.47
     concordance
    0.47
    Ⲕ
    0.46
    Activations Density 0.001%

    No Known Activations