© 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. 206384
    Prev
    Next
    INDEX
    Explanations

    contrast and wisdom

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

    exceeding descriptions

    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
     Feminist
    0.50
    َح
    0.46
    濒
    0.42
    墮
    0.41
     Femin
    0.41
    ᅨ
    0.41
    接觸
    0.41
    ujete
    0.40
    femin
    0.40
    𝐔
    0.40
    POSITIVE LOGITS
     illustrating
    0.54
     illustrations
    0.47
    Illustration
    0.46
     ylab
    0.46
    ちょ
    0.45
     illust
    0.44
    หลาย
    0.44
     điển
    0.43
    withId
    0.43
    ことができる
    0.43
    Activations Density 0.001%

    No Known Activations