© 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. 139671
    Prev
    Next
    INDEX
    Explanations

    zip code area

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

    technical requirements and design

    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
     turmeric
    0.52
     lags
    0.48
     phyto
    0.47
     π
    0.46
    毬
    0.46
     shoes
    0.45
     iri
    0.45
    躾
    0.45
     (
    0.45
     ketones
    0.45
    POSITIVE LOGITS
    Artista
    0.45
    Businesses
    0.44
    pèce
    0.44
     desenvolv
    0.44
    ulière
    0.43
     entreprene
    0.43
    igion
    0.43
    songwriter
    0.43
    甯
    0.43
    сту
    0.42
    Activations Density 0.001%

    No Known Activations