© 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. 59515
    Prev
    Next
    INDEX
    Explanations

    display fingerprint, issue, extended warranty

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

    specific lists or classifications

    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
    
    0.53
    MPI
    0.48
     VCO
    0.46
    ký
    0.44
    WAB
    0.44
     அவர்களிடம்
    0.43
     ultraviolet
    0.43
     атмос
    0.43
     bầu
    0.42
     అక్క
    0.42
    POSITIVE LOGITS
    ي
    0.47
    迌
    0.46
    حل
    0.45
    œil
    0.44
     terminus
    0.43
    етра
    0.43
    oszt
    0.43
    玩意
    0.43
    уд
    0.43
     参数
    0.43
    Activations Density 0.000%

    No Known Activations