© 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. 47954
    Prev
    Next
    INDEX
    Explanations

    these attributes

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

    scientific community

    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
    ’
    0.55
    :
    0.52
     others
    0.49
    ’;
    0.47
    0.46
     kong
    0.46
     innen
    0.46
     internation
    0.46
     cries
    0.46
    ↵↵↵
    0.45
    POSITIVE LOGITS
    म्मू
    0.50
    randomNumber
    0.48
    getName
    0.48
    bottlecap
    0.47
    routeProvider
    0.47
    getPrice
    0.47
    algèbre
    0.47
    getMain
    0.47
    ниці
    0.46
    íoch
    0.45
    Activations Density 0.000%

    No Known Activations