© 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. 58936
    Prev
    Next
    INDEX
    Explanations

    a HD camera

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

    detection gnome object Cat crib

    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
     exceedingly
    0.46
     Operation
    0.45
    滪
    0.45
    Accel
    0.44
    衄
    0.42
     Acquire
    0.42
     LIABILITY
    0.42
     incontro
    0.42
     somehow
    0.41
    Operation
    0.41
    POSITIVE LOGITS
     communes
    0.53
    glightbox
    0.53
     बृहस्पतिवार
    0.50
    来た
    0.47
     squats
    0.47
     alleys
    0.46
    駅
    0.46
    🫡
    0.46
     saludar
    0.45
     phonons
    0.45
    Activations Density 0.000%

    No Known Activations