© 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. 165388
    Prev
    Next
    INDEX
    Explanations

    listing requirements risk speaks

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

    rich topic

    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
    ūn
    0.50
    тельностью
    0.46
    enio
    0.43
    والفقار
    0.43
    последствии
    0.41
    भ
    0.41
     భారతదేశ
    0.41
    ड्या
    0.41
     tentunya
    0.41
    ört
    0.40
    POSITIVE LOGITS
     thermoelectric
    0.49
    稳定
    0.48
    Fract
    0.46
    范围
    0.45
    N
    0.45
    M
    0.45
    R
    0.44
    疯
    0.44
    Blanc
    0.43
    外し
    0.43
    Activations Density 0.000%

    No Known Activations