© 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. 234151
    Prev
    Next
    INDEX
    Explanations

    boarding pass

    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
    언
    0.49
    ื่น
    0.47
    뱀
    0.45
     क्वेश्चंस
    0.45
     Temperaturen
    0.42
    صد
    0.41
    グレ
    0.41
    ссмо
    0.41
    Соцмережа
    0.41
    לי
    0.40
    POSITIVE LOGITS
    t
    0.65
    saf
    0.52
    dés
    0.50
     extrémité
    0.49
    a
    0.49
     posiad
    0.48
    disabled
    0.48
    lact
    0.47
    d
    0.47
     injective
    0.46
    Activations Density 0.000%

    No Known Activations