© 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. 29561
    Prev
    Next
    INDEX
    Explanations

    optical fibers

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

    but followed by conjunctions

    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
    斬
    0.48
     sólidos
    0.43
     Kelas
    0.43
     empresa
    0.42
    干燥
    0.42
    的公司
    0.42
    .
    0.41
     şirk
    0.41
     Gases
    0.40
    借助
    0.40
    POSITIVE LOGITS
    quette
    0.49
    𒋾
    0.47
     bahsed
    0.46
    ThoughtData
    0.46
    oned
    0.45
    paired
    0.45
    lehem
    0.45
    ":"","
    0.45
    wärts
    0.44
     ό
    0.44
    Activations Density 0.000%

    No Known Activations