© 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. 99673
    Prev
    Next
    INDEX
    Explanations

    categories of items or events

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

    let $x$ or variable introduction

    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
     dibawa
    0.49
    kenalkan
    0.48
     поня
    0.48
    ?}",
    0.46
     بينهم
    0.46
     пово
    0.46
     mooi
    0.45
     simplifié
    0.45
     betray
    0.45
     bize
    0.44
    POSITIVE LOGITS
    द
    0.49
    ר
    0.49
    STATES
    0.48
    у
    0.48
    あなたが
    0.47
    τε
    0.46
    к
    0.46
    च
    0.46
    δ
    0.46
    Multiple
    0.45
    Activations Density 0.000%

    No Known Activations