© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 24767
    Prev
    Next
    INDEX
    Explanations

    Other Religions

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

    technical or formal-domain terms, tending toward longer, domain-specific vocabulary.

    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
    '));
    0.48
    可
    0.46
    𝘬
    0.46
    🔌
    0.45
    cies
    0.44
     quickest
    0.44
    メンズ
    0.43
     after
    0.43
    시간
    0.42
     easiest
    0.41
    POSITIVE LOGITS
     Phenomenology
    0.47
     phenomenology
    0.42
    腆
    0.42
    рида
    0.41
     ellipsoid
    0.40
     ез
    0.40
     Laguna
    0.40
     lebens
    0.40
     acque
    0.40
     autour
    0.39
    Activations Density 0.001%

    No Known Activations