© 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. 98753
    Prev
    Next
    INDEX
    Explanations

    booklet, documentary, Goodwill Industries

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

    wireless connectivity, chemical analysis, upgraded database

    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
    IVEN
    0.50
    ี
    0.49
    いっぱい
    0.48
    Ī
    0.48
     ایکس
    0.48
    низу
    0.47
    📩
    0.47
    彙
    0.47
    Ǘ
    0.46
    เรา
    0.46
    POSITIVE LOGITS
     adjuster
    0.53
     adhes
    0.50
     económicas
    0.49
     económico
    0.48
     defensive
    0.47
     lic
    0.47
     profits
    0.46
     adher
    0.46
     caut
    0.46
     bapt
    0.46
    Activations Density 0.000%

    No Known Activations