© 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. 150286
    Prev
    Next
    INDEX
    Explanations

    promote health awareness

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

    lists of terms and their follow-ups

    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
     attributed
    0.47
     propios
    0.46
     glorious
    0.46
     docile
    0.46
    ိုက်
    0.45
    寘
    0.45
     bölümde
    0.45
    ख्यात
    0.45
     Healey
    0.45
     próprio
    0.44
    POSITIVE LOGITS
    ้
    0.53
    ?>
    0.52
     promu
    0.50
    ын
    0.49
     มาก
    0.49
     บุ
    0.48
    ؟
    0.48
    ency
    0.47
     طا
    0.46
    ;?>
    0.46
    Activations Density 0.001%

    No Known Activations