© 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. 32816
    Prev
    Next
    INDEX
    Explanations

    social/cultural influences

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

    client-server and creative roles

    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
     undercut
    0.45
    스타
    0.44
     espos
    0.44
     Ato
    0.43
    날
    0.43
    탁
    0.43
    Pom
    0.41
    chill
    0.41
    راه
    0.41
     Devlet
    0.41
    POSITIVE LOGITS
     ଦ
    0.59
     variar
    0.50
     கதாபா
    0.48
    akal
    0.48
    affine
    0.48
    aff
    0.47
     ଜ
    0.47
    餾
    0.47
    ovní
    0.47
     cré
    0.47
    Activations Density 0.000%

    No Known Activations