© 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. 162357
    Prev
    Next
    INDEX
    Explanations

    people, cult, angels, Army

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

    names specific things, e.g. "articles"

    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
    तरे
    0.48
    迁移
    0.48
    backgroundImage
    0.47
     caricature
    0.47
     incumbent
    0.46
    ASF
    0.46
    ﻕ
    0.45
     myogenic
    0.44
    UIC
    0.44
     eddy
    0.44
    POSITIVE LOGITS
     約
    0.50
     받고
    0.50
    𝟘
    0.46
     जिसकी
    0.45
     ಈಗ
    0.45
     บวก
    0.44
     dren
    0.43
     जिसको
    0.43
    ilia
    0.42
    ܠܐ
    0.42
    Activations Density 0.001%

    No Known Activations