© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 76146
    Prev
    Next
    INDEX
    Explanations

    are you

    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
     a
    0.74
    ו
    0.68
    д
    0.66
     an
    0.64
    л
    0.64
    ル
    0.63
    ל
    0.63
     enlev
    0.60
    د
    0.57
    ل
    0.56
    POSITIVE LOGITS
    eli
    0.53
     Packers
    0.53
     lipids
    0.50
    neurons
    0.50
    wolves
    0.49
     polymers
    0.49
    <unused88>
    0.48
    icture
    0.48
    odings
    0.48
     ligaments
    0.47
    Activations Density 0.045%

    No Known Activations