© 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. 190365
    Prev
    Next
    INDEX
    Explanations

    laws and rights

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

    control and suggestions

    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
    મ
    0.46
    ائ
    0.46
    层面
    0.45
    方面
    0.45
    ettle
    0.45
     편리
    0.45
    供应
    0.44
    vive
    0.43
    公司
    0.43
    mot
    0.42
    POSITIVE LOGITS
    displayName
    0.47
    webElement
    0.46
    г
    0.44
    ogany
    0.44
    <>());
    0.43
    یثیت
    0.43
     inscr
    0.42
    '<
    0.41
    fullName
    0.41
     ov
    0.41
    Activations Density 0.001%

    No Known Activations