© 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. 76439
    Prev
    Next
    INDEX
    Explanations

    in conclusion, gather er

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

    culminating in value

    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
     ОС
    0.45
    Sign
    0.45
    Ó
    0.45
     עם
    0.44
    بر
    0.43
    holm
    0.42
    Tidak
    0.42
    Z
    0.42
     TODOS
    0.42
    ధం
    0.42
    POSITIVE LOGITS
     assays
    0.46
    вёр
    0.44
    ковые
    0.43
     yours
    0.41
     seekBar
    0.40
     assay
    0.40
    ेंद्रीय
    0.40
    uggish
    0.39
     trent
    0.39
     wastewater
    0.39
    Activations Density 0.002%

    No Known Activations