© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 17315
    Prev
    Next
    INDEX
    Explanations

    code and statistical formulas

    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
     Bit
    0.41
     y
    0.40
     or
    0.40
     cos
    0.40
     and
    0.39
    Bit
    0.39
     function
    0.39
     in
    0.38
     hip
    0.38
     Sar
    0.38
    POSITIVE LOGITS
    톄
    0.47
    oyeva
    0.46
    gmzy
    0.41
    avacanam
    0.40
    abhave
    0.40
    examtype
    0.39
    ुलकर
    0.39
    getCQL
    0.39
     इंग्ल
    0.39
     믿
    0.39
    Activations Density 0.091%

    No Known Activations