© 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. 143713
    Prev
    Next
    INDEX
    Explanations

    recipe book

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

    describing conditions and characteristics

    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
    ২৫
    0.55
    悅
    0.54
     অফিসে
    0.44
    তর
    0.43
    শিরোনাম
    0.43
    ולוג
    0.43
     điện
    0.43
    …</
    0.42
    GBuf
    0.42
    সম্প্রতি
    0.42
    POSITIVE LOGITS
    zo
    0.49
    usas
    0.49
    bere
    0.47
     grasslands
    0.47
    jetas
    0.46
    adura
    0.46
    ad
    0.46
    ritas
    0.46
    ikuti
    0.45
    z
    0.45
    Activations Density 0.000%

    No Known Activations