© 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. 212932
    Prev
    Next
    INDEX
    Explanations

    directions or locations

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

    action and impact verbs

    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
    Supplier
    0.48
     [],
    0.47
    ForgotPassword
    0.47
    Qty
    0.46
    =>{
    0.46
     mercenaries
    0.46
    LoginPage
    0.46
    pere
    0.46
    /***
    0.45
    的所有
    0.45
    POSITIVE LOGITS
    н
    0.53
    에
    0.52
    ան
    0.49
    ної
    0.49
    ні
    0.48
     westbound
    0.48
     northbound
    0.48
     southbound
    0.47
    ff
    0.47
     handout
    0.46
    Activations Density 0.001%

    No Known Activations