© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 81729
    Prev
    Next
    INDEX
    Explanations

    there's a

    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
    īg
    0.51
    ꯋ
    0.47
    💁
    0.47
     může
    0.47
     šť
    0.46
    ješ
    0.46
     💪
    0.46
    beren
    0.45
     hetzelfde
    0.45
    ⴳ
    0.45
    POSITIVE LOGITS
     tendency
    0.72
     possibility
    0.55
     discrepancy
    0.53
     necessity
    0.51
     fallacy
    0.49
     need
    0.49
     কারণে
    0.49
     danger
    0.48
     trend
    0.47
    趋势
    0.47
    Activations Density 0.020%

    No Known Activations