© 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. 1301
    Prev
    Next
    INDEX
    Explanations

    increase dividends

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

    mentions of domain-specific technical terms and model/product identifiers within instructional or explanatory text, especially when listing examples or specifications.

    oai_token-act-pair · gpt-5
    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
    ᅨ
    0.33
    ＮＡＮＡ
    0.32
    vykor
    0.30
     বলিয়াই
    0.29
    TARGETTING
    0.29
    OpportunitiesBy
    0.29
    सरकार
    0.29
    કિસ્
    0.29
     मुसलमान
    0.28
    歟
    0.28
    POSITIVE LOGITS
    ,
    0.47
     (
    0.42
     for
    0.37
    0.37
     à
    0.37
     For
    0.35
     A
    0.35
     to
    0.34
     +
    0.34
     de
    0.34
    Activations Density 1.441%

    No Known Activations