© 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. 28002
    Prev
    Next
    INDEX
    Explanations

    time, more, growth, duration

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

    your or specific endings

    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
     sempurna
    0.31
    ﺶ
    0.30
    ঙ্কা
    0.29
     dumplings
    0.29
    欵
    0.29
     servidores
    0.29
    ција
    0.29
    cstdio
    0.28
     cupcakes
    0.28
    νομ
    0.28
    POSITIVE LOGITS
    łach
    0.35
    ையே
    0.32
    acht
    0.31
     Cha
    0.31
    í
    0.31
    î
    0.31
    ong
    0.31
    ürich
    0.30
     Valley
    0.29
     हिस्ट्री
    0.29
    Activations Density 0.020%

    No Known Activations