© 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. 33116
    Prev
    Next
    INDEX
    Explanations

    get many or a

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

    get air

    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
     smartphone
    0.47
     Sexy
    0.44
     products
    0.43
     guitar
    0.43
    тели
    0.43
     e
    0.42
     kids
    0.42
     yao
    0.41
     produtos
    0.41
     genomes
    0.41
    POSITIVE LOGITS
    蒨
    0.47
     Excuse
    0.44
     orator
    0.42
    影响力
    0.42
    flage
    0.42
    ostasis
    0.41
     exasper
    0.41
    벌
    0.41
    ❦
    0.41
    équation
    0.40
    Activations Density 0.000%

    No Known Activations