© 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. 5965
    Prev
    Next
    INDEX
    Explanations

    information and availability

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

    area preferences

    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
    <start_of_turn>
    0.56
     protéines
    0.56
     nutrientes
    0.54
     lichaam
    0.53
    枴
    0.50
    ધાનસભા
    0.49
     बीमार
    0.49
     fermentation
    0.48
     provoquer
    0.48
    <unused92>
    0.48
    POSITIVE LOGITS
    ↵↵
    0.65
    ier
    0.57
    if
    0.55
    y
    0.54
    <start_of_image>
    0.54
    ↵
    0.53
    e
    0.52
    </strong>
    0.51
     I
    0.50
    I
    0.50
    Activations Density 0.032%

    No Known Activations