© 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. 177565
    Prev
    Next
    INDEX
    Explanations

    They need

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

    Translation and Safety categories

    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
     भागीदारी
    0.47
     boosters
    0.46
    angling
    0.46
    __);
    0.46
     bolstering
    0.44
    URL
    0.42
    Lato
    0.42
    Url
    0.42
     aiding
    0.42
     Up
    0.41
    POSITIVE LOGITS
    NOD
    0.48
     রাসেল
    0.48
    المل
    0.46
    <0x96>
    0.46
     obrá
    0.45
     خصوص
    0.45
    خصوص
    0.45
    שות
    0.45
    垨
    0.45
    柩
    0.45
    Activations Density 0.000%

    No Known Activations