© 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. 48474
    Prev
    Next
    INDEX
    Explanations

    strong work, consignee, swing tongue

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

    audio translation generics integration

    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
    璈
    0.52
    cześ
    0.50
    atuur
    0.50
    在
    0.49
    도
    0.49
    ının
    0.49
    importanza
    0.49
    acağı
    0.48
    赃
    0.47
    accesso
    0.47
    POSITIVE LOGITS
     harmonious
    0.51
     freestyle
    0.47
     automation
    0.47
     customer
    0.46
     creative
    0.46
     alphabet
    0.45
     simple
    0.45
     algebraic
    0.45
     unconventional
    0.45
     Hao
    0.45
    Activations Density 0.000%

    No Known Activations