© 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. 12133
    Prev
    Next
    INDEX
    Explanations

    newly announced events

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

    announcements and debuts

    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
    ですから
    0.59
     판단
    0.48
     grandeza
    0.48
     barbit
    0.47
     शास्त्र
    0.46
     ανθρώ
    0.46
     doctrina
    0.45
    醣
    0.45
     splendour
    0.44
     principi
    0.44
    POSITIVE LOGITS
     announced
    0.66
     annoncé
    0.62
    ২০
    0.57
     debuted
    0.57
     anunció
    0.55
     Announced
    0.55
     debuting
    0.55
     erneut
    0.53
    debut
    0.53
    umumkan
    0.53
    Activations Density 0.037%

    No Known Activations