© 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. 173555
    Prev
    Next
    INDEX
    Explanations

    job opportunities

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

    Libre Office Calc

    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
     SYN
    0.46
     Waik
    0.44
    "/>.
    0.40
     KIT
    0.39
     ‘
    0.39
    Cricket
    0.39
    olini
    0.38
    Carbon
    0.38
     -->
    0.38
     clutch
    0.38
    POSITIVE LOGITS
    ιστή
    0.52
     oftentimes
    0.50
    ബ്ര
    0.49
    माइंडर
    0.48
    고사
    0.47
     manifestly
    0.47
    펀
    0.47
     ஊ
    0.47
    ஊ
    0.47
    न्या
    0.46
    Activations Density 0.001%

    No Known Activations