© 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. 197420
    Prev
    Next
    INDEX
    Explanations

    financial and personal information

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

    edition, Jasmine, performed, JAM, dialect

    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
    ي
    0.49
    iegel
    0.47
    ot
    0.46
     Area
    0.46
     Assume
    0.46
    তে
    0.46
     assum
    0.45
    忄
    0.45
     изба
    0.45
    ে
    0.45
    POSITIVE LOGITS
     partes
    0.47
    saturated
    0.44
    CHANT
    0.43
     cierre
    0.43
    aturated
    0.42
    saturation
    0.41
    程度
    0.41
     captures
    0.41
     грошы
    0.40
     cuánto
    0.40
    Activations Density 0.000%

    No Known Activations