© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 34412
    Prev
    Next
    INDEX
    Explanations

    awards dinners

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

    numerical data and concepts

    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
    ковь
    0.52
     Comunicación
    0.51
    2
    0.50
    хой
    0.48
    ኔታ
    0.46
    Kathy
    0.46
    メージ
    0.46
     stumble
    0.46
    톄
    0.45
     diversify
    0.45
    POSITIVE LOGITS
    c
    0.54
    off
    0.49
     परप
    0.46
    Suitable
    0.46
     পৌর
    0.45
    dut
    0.45
    suitable
    0.45
     Suitable
    0.45
    Baseline
    0.45
    Transaction
    0.44
    Activations Density 0.000%

    No Known Activations