© 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. 30698
    Prev
    Next
    INDEX
    Explanations

    speaking for representing

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

    understanding information and actions

    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
    试图
    0.45
    文件中
    0.43
     considerations
    0.42
     files
    0.42
     लॉन्च
    0.41
    arlos
    0.40
     ladders
    0.40
    𝘫
    0.40
     fichiers
    0.40
    ก
    0.40
    POSITIVE LOGITS
     আমাদেরকে
    0.47
    ।”
    0.47
     .”
    0.46
    গণের
    0.44
     ແມ່ນ
    0.44
     মাঠ
    0.44
    ।’’
    0.44
    ).”
    0.43
     RasterModelGrid
    0.43
    genommen
    0.43
    Activations Density 0.001%

    No Known Activations