© 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. 155015
    Prev
    Next
    INDEX
    Explanations

    start followed by names

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

    provide context and example

    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
    ”
    0.47
     blas
    0.45
    %;
    0.44
     cot
    0.44
     collapsible
    0.43
    phosph
    0.42
     somma
    0.41
     diagnosed
    0.41
     cote
    0.41
     determined
    0.40
    POSITIVE LOGITS
     HAVING
    0.54
     CONCLUS
    0.49
    ДО
    0.48
     하면
    0.48
     минуту
    0.48
    완
    0.48
     встроен
    0.48
    Để
    0.47
     tendrá
    0.47
     RULES
    0.46
    Activations Density 0.000%

    No Known Activations