© 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. 168053
    Prev
    Next
    INDEX
    Explanations

    maintenance settings

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

    beingwaswhoappearances

    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
     ሌ
    0.58
     sincerely
    0.55
     Tendulkar
    0.54
     disprove
    0.54
     geleg
    0.52
     ሕ
    0.51
     Sağ
    0.51
     cevap
    0.50
     relegation
    0.50
     düz
    0.50
    POSITIVE LOGITS
    未
    0.52
    polynomial
    0.41
     Solids
    0.41
    <0xA2>
    0.40
    llib
    0.39
    k
    0.39
    orph
    0.39
    textbf
    0.38
    ओं
    0.38
    (
    0.38
    Activations Density 0.000%

    No Known Activations