© 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. 113250
    Prev
    Next
    INDEX
    Explanations

    regulator, wash, zoom, blues, checks, dads

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

    pastime, similar, within documents

    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
    Ί
    0.48
    Aku
    0.46
     Breite
    0.46
    Daten
    0.46
    垪
    0.46
    Marca
    0.45
    संस्करण
    0.45
    Visited
    0.45
    哠
    0.45
    Тер
    0.44
    POSITIVE LOGITS
     कुटु
    0.50
     부여
    0.48
    ulitan
    0.47
    ையின்
    0.46
     बिता
    0.46
    kta
    0.46
    abili
    0.45
    akaranam
    0.45
     기울
    0.45
     കുടുംബ
    0.44
    Activations Density 0.000%

    No Known Activations