© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 101447
    Prev
    Next
    INDEX
    Explanations

    abnormal dosage excessively rising

    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_all/layer_41_width_262k_l0_big
    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
     Henning
    0.40
    bei
    0.39
     дат
    0.39
    Hochspringen
    0.39
    จร
    0.38
     наших
    0.37
    ❅
    0.37
     открыть
    0.36
     öffnen
    0.36
     состоит
    0.36
    POSITIVE LOGITS
    endem
    0.42
    Ọ
    0.39
     functioning
    0.38
     capitalized
    0.38
    commun
    0.38
    資本
    0.37
    mmol
    0.36
    افئ
    0.36
     assoc
    0.36
     polyphen
    0.36
    Activations Density 2.205%

    No Known Activations