© 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. 53992
    Prev
    Next
    INDEX
    Explanations

    development and organisation

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

    iPhone Pro policy

    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
     merely
    0.46
     fian
    0.46
     किंवा
    0.44
     innych
    0.44
    i
    0.43
    仅仅
    0.42
     fix
    0.42
     یا
    0.41
     $$$
    0.40
    ي
    0.40
    POSITIVE LOGITS
    орга
    0.52
    役割
    0.47
    namefont
    0.47
    emplacement
    0.46
    LAYOUT
    0.46
    PARATION
    0.45
    เทศ
    0.45
    鳧
    0.45
    製の
    0.44
    attham
    0.44
    Activations Density 0.000%

    No Known Activations