© 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. 154855
    Prev
    Next
    INDEX
    Explanations

    gallery, click, web, once

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

    knowledge or, fire or, wait with

    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
    実感
    0.47
    みんな
    0.46
    一生
    0.45
    辐射
    0.45
    ÔNG
    0.44
    生き
    0.44
     повседнев
    0.44
    醗
    0.44
     그런
    0.44
     কর্ম
    0.43
    POSITIVE LOGITS
    ्री
    0.48
    olni
    0.45
     hurriedly
    0.42
    rang
    0.42
    volve
    0.41
     gil
    0.41
    vester
    0.41
    రికీ
    0.41
     Gilbert
    0.41
    ificantly
    0.41
    Activations Density 0.001%

    No Known Activations