© 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. 64076
    Prev
    Next
    INDEX
    Explanations

    foreign language and specific phrases

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

    sustainable food sources

    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
    不
    0.50
    deselect
    0.48
    static
    0.48
    name
    0.48
    あります
    0.47
    membrane
    0.46
    音が
    0.46
    hydrox
    0.45
    curs
    0.45
    operator
    0.45
    POSITIVE LOGITS
     extravag
    0.51
     퇴
    0.50
     Ко
    0.46
     extravagant
    0.45
     Та
    0.43
     설
    0.43
     ше
    0.43
     indulging
    0.42
     зазна
    0.42
     Tai
    0.42
    Activations Density 0.000%

    No Known Activations