© 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. 186495
    Prev
    Next
    INDEX
    Explanations

    electronic chip, virtual, long blades, again, often the, stimulate gross

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

    rules, copy, program, survey

    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
    <unused2173>
    0.44
     حقیقی
    0.43
    oble
    0.40
     एवं
    0.40
     thérapeut
    0.40
    ologie
    0.39
     полный
    0.38
     आलम
    0.38
     كلام
    0.38
     vào
    0.37
    POSITIVE LOGITS
     Finanz
    0.46
     東
    0.44
     Radon
    0.43
     stvari
    0.42
    xmlns
    0.41
     Ata
    0.41
     drugstore
    0.41
    梱
    0.41
     hå
    0.40
     Bezos
    0.40
    Activations Density 0.002%

    No Known Activations