© 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. 15203
    Prev
    Next
    INDEX
    Explanations

    following numbers and specific nouns

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

    closing punctuation and conjunctions

    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
    лық
    0.47
    を作
    0.47
     시민
    0.45
     만들
    0.45
     государственный
    0.45
     ప్రభుత్వ
    0.44
    运动
    0.43
    온
    0.43
    新技术
    0.43
    切实
    0.43
    POSITIVE LOGITS
    tables
    0.50
     rescind
    0.48
    deselect
    0.42
     paragraphe
    0.42
    ed
    0.42
    re
    0.42
     rembour
    0.42
    y
    0.42
    as
    0.41
     Treas
    0.40
    Activations Density 0.000%

    No Known Activations