© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 5136
    Prev
    Next
    INDEX
    Explanations

    values between 0 and 1

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    俱乐
    0.54
     책임
    0.53
    权力
    0.53
    ἢ
    0.52
    ेलकम
    0.52
    sbom
    0.51
    职务
    0.50
    acariy
    0.49
    缝
    0.49
    责任
    0.49
    POSITIVE LOGITS
     amplitude
    0.91
     grayscale
    0.89
     scaling
    0.88
     amplitudes
    0.82
     values
    0.82
     gradient
    0.82
     brightness
    0.80
     Gaussian
    0.79
     normalized
    0.77
     range
    0.77
    Activations Density 0.360%

    No Known Activations