© 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. 222121
    Prev
    Next
    INDEX
    Explanations

    life stages and states

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

    appointment, date, or time

    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
    fate
    0.43
    ରି
    0.43
     पिंडदान
    0.41
    ply
    0.41
    胄
    0.41
     wetting
    0.40
    flutter
    0.40
    media
    0.40
    мі
    0.39
     Technologies
    0.39
    POSITIVE LOGITS
     לק
    0.56
     aprend
    0.50
     אחר
    0.49
    }[\
    0.48
     לס
    0.46
    ;
    0.46
     racks
    0.46
     בס
    0.46
    敂
    0.46
    出一个
    0.46
    Activations Density 0.000%

    No Known Activations