© 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. 53020
    Prev
    Next
    INDEX
    Explanations

    questions and lyrics

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

    know how to use

    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
    роне
    0.54
    РИ
    0.48
    ก
    0.47
    רה
    0.46
    на
    0.45
    stability
    0.45
    覤
    0.44
    sk
    0.43
    gä
    0.43
    ร
    0.42
    POSITIVE LOGITS
     pedibus
    0.53
     Ballot
    0.50
     Graffiti
    0.48
     Bicycle
    0.45
     durant
    0.45
     स्कूलों
    0.44
     সুযোগ
    0.44
     suburban
    0.44
     Teacher
    0.43
     quindi
    0.43
    Activations Density 0.000%

    No Known Activations