© 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. 238513
    Prev
    Next
    INDEX
    Explanations

    No part of

    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
    ທີ່ຈະ
    0.54
    <unused17>
    0.48
     મહિના
    0.48
    다라고
    0.47
    يج
    0.46
    JY
    0.46
    FURNIZOR
    0.45
    ƾ
    0.45
    ção
    0.45
    <unused64>
    0.45
    POSITIVE LOGITS
    ’
    0.49
     this
    0.46
     would
    0.45
     may
    0.45
     is
    0.44
    ons
    0.44
    ols
    0.44
     sounds
    0.44
     derived
    0.43
     Derived
    0.43
    Activations Density 0.000%

    No Known Activations