© 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. 250797
    Prev
    Next
    INDEX
    Explanations

    specific terms and phrases

    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
    াকের
    0.56
    >©
    0.46
     demo
    0.46
     beer
    0.44
     organics
    0.44
     arroz
    0.43
     organic
    0.43
     blue
    0.43
     rapides
    0.42
    ামে
    0.42
    POSITIVE LOGITS
     問
    0.53
     材質
    0.49
    돕
    0.48
     हिम्मत
    0.48
     신고
    0.47
    폼
    0.47
     ಕೂಡ
    0.47
     剤
    0.47
    érance
    0.46
     Pneum
    0.46
    Activations Density 0.000%

    No Known Activations