© 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. 218548
    Prev
    Next
    INDEX
    Explanations

    standards and specifications

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

    specific details or 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
     Zel
    0.44
     Kurt
    0.40
     تعلمنا
    0.40
     Cub
    0.40
    افظ
    0.40
    榛
    0.39
     Latino
    0.39
     Página
    0.38
     Bastian
    0.38
     Victor
    0.38
    POSITIVE LOGITS
    ARY
    0.60
    arys
    0.56
    i
    0.55
     playerId
    0.54
     thefts
    0.54
     commencing
    0.52
     refineries
    0.52
     clearances
    0.51
    remainder
    0.50
     theatres
    0.50
    Activations Density 0.000%

    No Known Activations