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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 15250
    Prev
    Next
    INDEX
    Explanations

    slide rules, cloak username

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

    apostrophe-based contractions and possessive forms in 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
     ある
    0.35
     まず
    0.34
     同じ
    0.33
    ca
    0.33
     ட
    0.32
    bilical
    0.32
    뭘
    0.32
    large
    0.31
     izay
    0.31
     abdom
    0.31
    POSITIVE LOGITS
     shenanigans
    0.37
     was
    0.37
     được
    0.34
    ücke
    0.34
    应对
    0.34
     selfless
    0.34
     galore
    0.33
    快捷
    0.33
     gifting
    0.33
    을
    0.33
    Activations Density 0.178%

    No Known Activations