© 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. 142036
    Prev
    Next
    INDEX
    Explanations

    numbers and counts

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

    numbers and quantities

    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
    嬅
    0.45
    bereitung
    0.42
    डाय
    0.42
    ARIOS
    0.42
    aphys
    0.41
     Zeus
    0.41
    де
    0.40
    ơi
    0.40
    캉
    0.40
     Camps
    0.40
    POSITIVE LOGITS
     hundred
    0.74
     dozen
    0.68
     thousand
    0.66
    hundred
    0.54
     centena
    0.50
     ಸಾವಿರ
    0.50
     puluh
    0.48
     hundert
    0.48
     Luckily
    0.47
    thousand
    0.47
    Activations Density 0.019%

    No Known Activations