© 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. 86537
    Prev
    Next
    INDEX
    Explanations

    picked up, his head, its opening

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

    describing complex Azure parameters

    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
     zipped
    0.46
     eased
    0.43
     gooey
    0.43
    ിയുടെ
    0.42
     amassed
    0.42
     FFT
    0.41
     Dap
    0.41
    -/
    0.41
     Therapeutics
    0.40
     undeniably
    0.40
    POSITIVE LOGITS
     ቤ
    0.42
    ن
    0.42
    迁
    0.40
    inafter
    0.40
    中村
    0.40
    गढ़
    0.40
    喇
    0.39
    ป
    0.39
    崇
    0.39
    SERVICE
    0.38
    Activations Density 0.000%

    No Known Activations