© 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. 211435
    Prev
    Next
    INDEX
    Explanations

    add or not add

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

    medical and data structure descriptions

    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
     Khalid
    0.45
    𝐢
    0.45
     alebo
    0.44
     spielte
    0.44
     stelle
    0.44
     úlo
    0.43
     ilyen
    0.43
     stella
    0.42
    ୀ
    0.42
     комби
    0.42
    POSITIVE LOGITS
     Council
    0.44
    ão
    0.44
     돼
    0.44
    ress
    0.44
    '(
    0.43
     (
    0.42
    effer
    0.41
     قیام
    0.41
    נן
    0.41
    ור
    0.40
    Activations Density 0.002%

    No Known Activations