© 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. 245600
    Prev
    Next
    INDEX
    Explanations

    saying, Our, Tips, here

    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
    ome
    0.56
    mos
    0.48
    კო
    0.48
    મ
    0.48
    ند
    0.47
    λού
    0.47
    iment
    0.47
    pressure
    0.46
    ίσ
    0.45
    tense
    0.45
    POSITIVE LOGITS
     ${
    0.54
     output
    0.53
     alleges
    0.49
    $\\
    0.49
     cartridges
    0.48
    $...
    0.47
    =”
    0.47
    output
    0.46
     Output
    0.46
     powders
    0.46
    Activations Density 0.001%

    No Known Activations