© 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. 46819
    Prev
    Next
    INDEX
    Explanations

    multi-lingual choice

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

    get him to a vet

    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
    -
    0.70
     o
    0.51
    (
    0.51
     vertes
    0.50
     isten
    0.49
    y
    0.47
     vari
    0.46
     orbit
    0.46
    vat
    0.46
    –
    0.45
    POSITIVE LOGITS
    ментов
    0.49
     संवै
    0.46
    Idioma
    0.46
     मुसी
    0.45
     बुन
    0.45
     پیسہ
    0.43
    많은
    0.43
    sidenav
    0.43
     गुप्त
    0.42
     मच्छ
    0.42
    Activations Density 0.000%

    No Known Activations