© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 99552
    Prev
    Next
    INDEX
    Explanations

    regional level

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

    diffusion process

    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
     kriy
    0.60
     shabd
    0.51
     vutt
    0.48
     більш
    0.48
     bardziej
    0.48
     ważne
    0.48
     intricately
    0.47
    <unused64>
    0.47
     chhoti
    0.47
     énfasis
    0.46
    POSITIVE LOGITS
    <0xE3>
    0.55
    begin
    0.47
    {
    0.46
    走
    0.46
    起
    0.43
    (
    0.42
    ба
    0.42
    тро
    0.41
    树
    0.41
    Attack
    0.41
    Activations Density 0.000%

    No Known Activations