© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 5258
    Prev
    Next
    INDEX
    Explanations

    UI buttons and elements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     stoichi
    0.39
    URNIZOR
    0.39
     assays
    0.37
    embryon
    0.37
     htob
    0.35
     parthenogenetic
    0.35
     criteri
    0.35
    <unused0>
    0.34
    Hvis
    0.34
     probative
    0.34
    POSITIVE LOGITS
     Main
    0.37
     footer
    0.34
     Icons
    0.34
     Button
    0.34
     Buttons
    0.33
     Services
    0.33
     button
    0.33
     News
    0.32
     Gallery
    0.32
     Home
    0.32
    Activations Density 0.091%

    No Known Activations