© 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. 109740
    Prev
    Next
    INDEX
    Explanations

    something (you) can

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

    analyzing and monitoring conditions

    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
    享受
    0.47
     groupings
    0.44
     venting
    0.43
     projections
    0.42
    预
    0.42
    虽然
    0.42
     வாய்ப்ப
    0.42
     enjoying
    0.41
     즐
    0.41
    提
    0.41
    POSITIVE LOGITS
    निर
    0.52
     malos
    0.50
    TEGER
    0.49
     Hunan
    0.48
    urte
    0.48
     localizar
    0.47
    verifier
    0.47
     சிலையை
    0.46
    businessman
    0.46
     行っ
    0.46
    Activations Density 0.005%

    No Known Activations