© 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. 74243
    Prev
    Next
    INDEX
    Explanations

    quotes and foreign words

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

    code formatting and structure

    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
    EN
    0.71
    AR
    0.67
    ENTAL
    0.61
    >
    0.59
    OS
    0.58
    ENT
    0.57
    YE
    0.55
     MA
    0.55
    n
    0.55
    IN
    0.53
    POSITIVE LOGITS
    γρα
    0.55
    νο
    0.55
     තර
    0.54
    нда
    0.52
    uvres
    0.51
    мето
    0.50
     multitudes
    0.50
     це
    0.50
     осигурање
    0.50
    проце
    0.49
    Activations Density 0.002%

    No Known Activations