© 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. 40164
    Prev
    Next
    INDEX
    Explanations

    important AI disclaimers

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

    tokens used for emphasis or section headers (e.g., bold/asterisk markers and words like "Important"/"Disclaimer").

    oai_token-act-pair · gpt-5-miniTriggered 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
    uminous
    0.43
     spruce
    0.41
    䢌
    0.40
     disperse
    0.40
     sanat
    0.39
     തൂ
    0.39
     deceler
    0.39
     publica
    0.39
    }");
    0.39
     diventa
    0.39
    POSITIVE LOGITS
     каждого
    0.45
     разговор
    0.44
     лично
    0.44
     помога
    0.44
     상당
    0.43
     personnes
    0.43
     kişiler
    0.42
     personas
    0.42
    ེ
    0.42
    ployed
    0.41
    Activations Density 0.002%

    No Known Activations