© 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-16K
    7. 12549
    Prev
    Next
    INDEX
    Explanations

    all pairs shortest path

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

    code syntax patterns

    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_16k_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
    april
    0.46
    iping
    0.45
    artic
    0.45
    #$%
    0.43
    adrat
    0.42
     voting
    0.42
     holotype
    0.41
    ignation
    0.41
    iverr
    0.41
    name
    0.41
    POSITIVE LOGITS
     উপদে
    0.46
    Cumulative
    0.44
    鎧
    0.44
    累
    0.42
     GUARD
    0.41
    Summar
    0.41
    DAG
    0.41
    DP
    0.41
    cumulative
    0.41
    SSE
    0.40
    Activations Density 0.007%

    No Known Activations