© 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. 139398
    Prev
    Next
    INDEX
    Explanations

    many.io / .io games

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

    team, backups, comparing, mention

    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
     कराई
    0.58
    搡
    0.48
    谅
    0.48
    โน
    0.46
     Campaign
    0.45
     Cer
    0.44
     Coyote
    0.42
    ৬
    0.42
    鼗
    0.42
    挲
    0.42
    POSITIVE LOGITS
     \
    0.53
    ,“
    0.52
     wyniku
    0.50
    ,_-
    0.47
     tellement
    0.45
    VING
    0.45
     /(
    0.45
    för
    0.44
    “
    0.44
                    
    0.43
    Activations Density 0.001%

    No Known Activations