© 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. 162191
    Prev
    Next
    INDEX
    Explanations

    table, articles, promise, wanting

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

    types of queries

    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
     유사
    0.51
     novel
    0.48
     bus
    0.46
     inext
    0.46
     명
    0.46
     warmer
    0.46
     หลัง
    0.46
     cray
    0.45
     niên
    0.45
     아마
    0.45
    POSITIVE LOGITS
    дете
    0.53
    你
    0.51
    talent
    0.49
     você
    0.47
    rolls
    0.47
    typicode
    0.46
     zusätzlich
    0.46
    “-
    0.45
    detached
    0.45
    tabla
    0.44
    Activations Density 0.000%

    No Known Activations