© 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. 64756
    Prev
    Next
    INDEX
    Explanations

    restore action

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

    undo redo

    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
     fiind
    0.42
     skipped
    0.41
     الجديد
    0.38
     disregarded
    0.38
    <sup>
    0.38
     remained
    0.37
    াধিক
    0.37
    <0xE3>
    0.37
     proudly
    0.36
     withdrew
    0.36
    POSITIVE LOGITS
    லய
    0.47
    hairstyle
    0.46
     аллер
    0.46
     तापमान
    0.46
    лли
    0.45
    ிலி
    0.45
    ोगे
    0.45
    पना
    0.45
    punt
    0.45
    मध
    0.44
    Activations Density 0.001%

    No Known Activations