© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 18992
    Prev
    Next
    INDEX
    Explanations

    psychosis and eosinophils

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

    medical and psychiatric terms related to psychosis and schizophrenia.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    蹰
    -2.89
    逦
    -2.69
    踽
    -2.50
     руке
    -2.48
     meditative
    -2.38
    ا
    -2.36
    孭
    -2.36
    u
    -2.28
     $*$
    -2.28
    <bos>
    -2.23
    POSITIVE LOGITS
     This
    3.09
    ࣭
    2.91
    4
    2.72
    咴
    2.67
    肫
    2.64
     १
    2.63
    ing
    2.58
     u
    2.53
    </sup>
    2.47
    n
    2.39
    Activations Density 0.006%

    No Known Activations