© 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. 164792
    Prev
    Next
    INDEX
    Explanations

    time durations and locations

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

    list items and structure markers

    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
     والذي
    0.43
    '}$
    0.41
     laug
    0.40
    jek
    0.40
    訟
    0.39
     Gruppen
    0.39
    䏌
    0.39
    屒
    0.39
    kovskij
    0.38
    عه
    0.38
    POSITIVE LOGITS
     RECEIVED
    0.54
    ड़ाई
    0.53
     focusing
    0.52
     biosynthesis
    0.51
     recibido
    0.50
    <0x8D>
    0.50
     copying
    0.50
     diethyl
    0.50
     RELEASE
    0.49
     gare
    0.49
    Activations Density 0.000%

    No Known Activations