© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 98330
    Prev
    Next
    INDEX
    Explanations

    New York, browser, company, magnet

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     maanden
    0.40
     joints
    0.40
     Timeout
    0.40
    ningen
    0.39
    മിന്റെ
    0.39
    닝
    0.39
     previo
    0.39
     joint
    0.39
    blad
    0.39
     crews
    0.38
    POSITIVE LOGITS
    深受
    0.45
     есть
    0.39
    Featuring
    0.36
    ieť
    0.36
    等地
    0.36
     быть
    0.35
    accès
    0.35
    Formerly
    0.35
    Gee
    0.34
    ༣
    0.34
    Activations Density 0.000%

    No Known Activations