© 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. 24847
    Prev
    Next
    INDEX
    Explanations

    physical descriptions like ill. or sound

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

    its orientation

    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
    秸
    0.52
    нице
    0.50
     청바
    0.44
    ниці
    0.43
    貉
    0.43
     টাকার
    0.43
    BeforeText
    0.43
    可以选择
    0.42
    вший
    0.42
     सवारी
    0.42
    POSITIVE LOGITS
     gigantic
    0.44
     massive
    0.42
     großer
    0.42
     colossal
    0.42
     enormous
    0.41
     spiral
    0.41
    damaged
    0.41
    ↵
    0.41
     depl
    0.41
     damaged
    0.40
    Activations Density 0.000%

    No Known Activations