© 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. 116352
    Prev
    Next
    INDEX
    Explanations

    venue names

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

    Fisherman's Wharf, authorization, Iraq

    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
     grinders
    0.52
     aparel
    0.52
     killers
    0.51
    bible
    0.49
     underlines
    0.47
     rulers
    0.46
    鲷
    0.46
     appareils
    0.45
     oscillators
    0.44
     quilts
    0.44
    POSITIVE LOGITS
    να
    0.47
    加盟
    0.46
    。",
    0.46
    علي
    0.44
    ương
    0.44
    дна
    0.44
    נ
    0.43
     किया
    0.43
     स्वीकृत
    0.43
    เภอ
    0.42
    Activations Density 0.000%

    No Known Activations