© 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. 71591
    Prev
    Next
    INDEX
    Explanations

    industry parameters

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

    imaginary glasses, headset, virginity

    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
    க
    0.48
    ල
    0.47
    접
    0.46
     sizzling
    0.45
    на
    0.44
    പ്പം
    0.44
    ലോ
    0.44
     జీ
    0.44
     Selecting
    0.44
    滖
    0.42
    POSITIVE LOGITS
    Mou
    0.49
    Automation
    0.47
    Quer
    0.47
    Drone
    0.45
     تکن
    0.45
    otechnology
    0.44
    電動
    0.44
    Ler
    0.44
    lac
    0.44
    PLA
    0.44
    Activations Density 0.001%

    No Known Activations