© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 2316
    Prev
    Next
    INDEX
    Explanations

    based on financial or technical details

    np_acts-logits-general · gemini-2.5-flash-lite

    tokens that occur in the assistant's long, explanatory reply text — especially opening/discourse tokens (like "Okay,") and other words in extended model-generated responses.

    oai_token-act-pair · gpt-5-mini
    Triggered by @vetterc0
    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
    Negative Logits
    myButtons
    0.52
    ड़ने
    0.52
    ಂಟು
    0.49
     придется
    0.49
     bisog
    0.49
    кость
    0.48
     quaisquer
    0.48
    אים
    0.47
     Polaribacter
    0.47
    ान्य
    0.47
    POSITIVE LOGITS
    github
    0.53
     (
    0.51
    Cl
    0.49
    ref
    0.47
    seed
    0.47
    static
    0.46
    water
    0.46
    line
    0.46
    ll
    0.45
    style
    0.45
    Activations Density 0.001%

    No Known Activations