© 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. 20660
    Prev
    Next
    INDEX
    Explanations

    list items or bullet points

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

    structured, expository formatting cues—headings, labeled fields, and numbered or bulleted list items, often with parenthetical examples and dates/times.

    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
    3
    0.40
    6
    0.39
     சிலர்
    0.37
    ovne
    0.36
    2
    0.34
    ６
    0.33
    1
    0.33
    5
    0.33
    텐
    0.32
    4
    0.32
    POSITIVE LOGITS
     usato
    0.38
     benutzer
    0.37
     conosci
    0.36
     verwend
    0.36
     squiggle
    0.35
     leistungs
    0.35
     graphon
    0.35
     explo
    0.34
     groovy
    0.34
     obscene
    0.34
    Activations Density 0.278%

    No Known Activations