© 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. 39834
    Prev
    Next
    INDEX
    Explanations

    bonus balance, doing writing, $9, history, my way

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

    corresponding values, constantly questioning

    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
    ᅥ
    0.49
     informé
    0.47
     attaining
    0.46
    ᱷ
    0.46
    フト
    0.46
    ン
    0.46
    informations
    0.45
    나
    0.45
    യ
    0.45
    際
    0.45
    POSITIVE LOGITS
     X
    0.52
     מש
    0.50
     prequel
    0.50
     berpikir
    0.49
     pikir
    0.49
     Nintendo
    0.46
     tanda
    0.46
     правила
    0.46
     propone
    0.45
     multiverse
    0.45
    Activations Density 0.000%

    No Known Activations