© 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. 181730
    Prev
    Next
    INDEX
    Explanations

    creation and action

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

    conditions or initial states

    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
    Asimismo
    0.51
     списке
    0.46
     Fiziki
    0.46
    퀵
    0.45
    RET
    0.44
    OPTIONS
    0.44
     soluciones
    0.44
     पढ़ेंः
    0.44
    Tarjeta
    0.44
     Etiquetas
    0.44
    POSITIVE LOGITS
     exon
    0.52
     soon
    0.50
    maker
    0.49
     w
    0.48
     semble
    0.48
     when
    0.48
    nom
    0.47
     some
    0.46
     teria
    0.46
    chym
    0.46
    Activations Density 0.000%

    No Known Activations