© 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. 164091
    Prev
    Next
    INDEX
    Explanations

    developments and analysis

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

    languages, code, and technical terms

    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
    h
    0.49
    Weather
    0.48
    ご確認
    0.46
     supervisors
    0.45
    struck
    0.44
     pels
    0.44
    řel
    0.44
    lots
    0.43
     Brend
    0.43
     tov
    0.43
    POSITIVE LOGITS
     ニュー
    0.50
     αυτο
    0.48
     maca
    0.47
     玄
    0.47
     разви
    0.47
     টেলিভিশন
    0.46
     entwickelte
    0.46
     thrombocyt
    0.45
     mengembangkan
    0.45
     原因
    0.45
    Activations Density 0.000%

    No Known Activations