© 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. 8888
    Prev
    Next
    INDEX
    Explanations

    automatic responses

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

    parenthetical or quoted example phrases and explanatory asides within instructional or explanatory text.

    oai_token-act-pair · gpt-5Triggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    ڍ
    0.36
     Substituting
    0.35
     Jesu
    0.34
    ercise
    0.34
     रखते
    0.33
    ጅ
    0.33
    STITUTION
    0.32
    ecd
    0.32
     வேற
    0.32
     ஐ
    0.31
    POSITIVE LOGITS
     receives
    0.63
     responded
    0.61
    ได้รับการ
    0.55
     automatic
    0.54
    会被
    0.53
     автоматически
    0.53
     receive
    0.52
     response
    0.52
    Automatically
    0.52
     получает
    0.52
    Activations Density 0.189%

    No Known Activations