© 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. 48738
    Prev
    Next
    INDEX
    Explanations

    your questions or advice

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

    operational blueprint

    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
    ｐ
    0.44
    пси
    0.40
    ！！！！
    0.39
     Cromwell
    0.38
     그죠
    0.37
    étrica
    0.37
     allez
    0.36
     ！
    0.36
     IV
    0.34
     Madrid
    0.34
    POSITIVE LOGITS
    Beware
    0.50
    You
    0.46
    Our
    0.46
    Your
    0.45
    What
    0.44
    Secure
    0.43
    »:
    0.42
    Keep
    0.42
    નો
    0.42
    Housing
    0.42
    Activations Density 0.031%

    No Known Activations