© 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. 48759
    Prev
    Next
    INDEX
    Explanations

    counting, spent, bit, usual, with, the, emerge, is

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

    quantities and timings

    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
    inspector
    0.43
     Cheung
    0.42
    ufficient
    0.41
     appropriate
    0.40
    *
    0.40
    ux
    0.40
     Ang
    0.39
    ibley
    0.38
     sufficient
    0.38
     Sufficient
    0.38
    POSITIVE LOGITS
     richesse
    0.45
     الامر
    0.43
    زمانہ
    0.42
     świata
    0.41
     protagonisti
    0.41
     düny
    0.40
     값을
    0.40
    ReaderWriter
    0.38
    ૢ
    0.38
     eeuw
    0.38
    Activations Density 0.000%

    No Known Activations