© 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-16K
    7. 1808
    Prev
    Next
    INDEX
    Explanations

    no significant conclusive

    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_16k_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
     dotyczą
    0.30
     execute
    0.29
     specify
    0.29
    ovania
    0.27
     Bedürfnisse
    0.27
    ឬ
    0.26
     expose
    0.26
     Dinge
    0.25
    㗽
    0.25
     wygl
    0.25
    POSITIVE LOGITS
    1
    0.32
     a
    0.31
     நியூ
    0.30
     مصنوعی
    0.30
     سیک
    0.29
    ب
    0.29
    های
    0.28
     one
    0.28
    めの
    0.28
    可能です
    0.28
    Activations Density 0.188%

    No Known Activations