© 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. 24434
    Prev
    Next
    INDEX
    Explanations

    and then choose

    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
     发
    0.51
     –
    0.47
     爱
    0.45
     项目
    0.44
     berarti
    0.42
    听
    0.42
    工业
    0.42
    营收
    0.42
     quilt
    0.41
    了个
    0.41
    POSITIVE LOGITS
    또한
    0.82
     또한
    0.78
     همچنین
    0.78
     також
    0.76
     zároveň
    0.75
     secondly
    0.74
    also
    0.73
     furthermore
    0.73
     također
    0.71
     также
    0.70
    Activations Density 0.032%

    No Known Activations