© 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. 135913
    Prev
    Next
    INDEX
    Explanations

    licenses, insurance, difficulties

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

    licenses

    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
    ъек
    0.54
     ጭ
    0.52
     Gebrauch
    0.49
     ጨ
    0.48
    authent
    0.48
    ėd
    0.47
     سيد
    0.47
     ପ୍ର
    0.46
     ව
    0.46
     linéaire
    0.46
    POSITIVE LOGITS
    <0xB6>
    0.53
     licensure
    0.48
    Licenses
    0.47
    .
    0.46
    .<
    0.45
     clock
    0.44
    ITIES
    0.44
    .</
    0.44
    .]
    0.44
    .”
    0.43
    Activations Density 0.000%

    No Known Activations