© 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. 155022
    Prev
    Next
    INDEX
    Explanations

    conferences, requirements, locations

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

    abilities and actions

    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
    MenuBar
    0.54
     fãs
    0.51
    REF
    0.47
    掌控
    0.45
    හ
    0.44
     salário
    0.44
    Retour
    0.44
     pacote
    0.44
    시
    0.44
    一份
    0.43
    POSITIVE LOGITS
     जिसे
    0.47
     tennis
    0.46
    ವಾಡ
    0.46
    ડો
    0.46
    হইতে
    0.45
    ators
    0.45
    atured
    0.45
    kové
    0.44
    olding
    0.43
    ukuran
    0.43
    Activations Density 0.000%

    No Known Activations