© 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. 242969
    Prev
    Next
    INDEX
    Explanations

    retention obligations, record video, suggestions based

    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
    擁有
    0.46
    ੁੰ
    0.46
    Getting
    0.45
    ೌ
    0.45
    ο
    0.45
    ಾ
    0.45
    themed
    0.44
    eno
    0.43
    ഖ
    0.43
    ौर
    0.42
    POSITIVE LOGITS
     dönd
    0.52
     сосед
    0.48
     második
    0.45
     Palms
    0.44
     dün
    0.43
     mağ
    0.41
     недалеко
    0.41
     ric
    0.41
     какво
    0.41
     erstmals
    0.40
    Activations Density 0.003%

    No Known Activations