© 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. 40-GEMMASCOPE-2-RES-262K
    7. 136002
    Prev
    Next
    INDEX
    Explanations

    map connecting points

    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_40_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
     betrayed
    0.40
     फरार
    0.37
     şeh
    0.36
    ۜ
    0.35
     br
    0.34
     Bracelet
    0.34
    ѓ
    0.34
    掰
    0.34
    ujourd
    0.34
     nonostante
    0.33
    POSITIVE LOGITS
     पोलीस
    0.40
    수로
    0.39
     نمونه
    0.39
     indent
    0.38
    DHL
    0.38
     susceptible
    0.37
     Proverbs
    0.36
     মূলত
    0.36
     alto
    0.36
     susceptibility
    0.36
    Activations Density 0.000%

    No Known Activations