© 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. 117748
    Prev
    Next
    INDEX
    Explanations

    loan periods, library, land obstacle

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

    enough sweeter

    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
    鈞
    0.46
    ನೇ
    0.45
    do
    0.43
     ભારત
    0.43
    l
    0.42
    nome
    0.42
    scanf
    0.42
    $.
    0.42
    இந்திய
    0.41
    𝗼
    0.41
    POSITIVE LOGITS
     hibernation
    0.52
     regenerating
    0.47
     intermission
    0.47
     confinement
    0.47
     splashing
    0.47
     landowner
    0.47
     উদ
    0.46
     regenerative
    0.46
     regeneration
    0.46
     unsuccessfully
    0.46
    Activations Density 0.000%

    No Known Activations