© 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. 142261
    Prev
    Next
    INDEX
    Explanations

    can help

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

    categorizing activities, time, and capabilities

    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
    ’
    0.48
    resist
    0.45
    arsenic
    0.44
    0.44
    with
    0.44
    anticipated
    0.44
    addies
    0.43
     stabilizes
    0.43
    皐
    0.42
    rm
    0.42
    POSITIVE LOGITS
     või
    0.50
     அல்லது
    0.50
    ihull
    0.49
     vagy
    0.47
     hyperplane
    0.46
    ьера
    0.46
     hoặc
    0.45
    корд
    0.45
    髖
    0.45
     cooldown
    0.45
    Activations Density 0.000%

    No Known Activations