© 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. 24165
    Prev
    Next
    INDEX
    Explanations

    convert to other forms

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

    conversion requests

    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
    保存
    0.48
    out
    0.42
    外
    0.41
     普通
    0.41
    )：
    0.40
    光学
    0.40
    金
    0.40
    符合
    0.39
     annual
    0.39
    ানোর
    0.38
    POSITIVE LOGITS
     posséd
    0.44
     bronchitis
    0.43
     toit
    0.42
     déficit
    0.42
     fièvre
    0.41
     തമ്മ
    0.41
     besi
    0.41
     Prothorax
    0.41
     mettant
    0.41
    itamins
    0.41
    Activations Density 0.000%

    No Known Activations