© 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. 41048
    Prev
    Next
    INDEX
    Explanations

    personal preference

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

    money, customers, time, positive

    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
    𝐌
    0.53
    mimeTypes
    0.46
    মন্ত
    0.45
    ী
    0.44
     المثلث
    0.44
    ת
    0.43
     aggrieved
    0.42
     الحكومة
    0.42
     স্বায়
    0.42
    ین
    0.41
    POSITIVE LOGITS
    春节
    0.46
     spreadsheet
    0.45
    方針
    0.45
    रोप
    0.45
     pract
    0.43
     journey
    0.43
    '
    0.43
    滘
    0.43
     sheet
    0.43
     sketchbook
    0.42
    Activations Density 0.000%

    No Known Activations