© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 73540
    Prev
    Next
    INDEX
    Explanations

    two-step reactions

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

    chemical formulas and notation in scientific and technical texts.

    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_34/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
     valueForKey
    -0.84
    nivå
    -0.82
    ѯ
    -0.81
    чему
    -0.81
    𓂅
    -0.79
    коны
    -0.79
    ardos
    -0.78
    約
    -0.78
    修改
    -0.77
     утра
    -0.77
    POSITIVE LOGITS
     disgu
    0.82
    Atten
    0.77
     Wages
    0.74
     consolidation
    0.74
    Brat
    0.74
     horny
    0.73
    ✳
    0.72
    メン
    0.72
     two
    0.71
     Instinct
    0.71
    Activations Density 0.001%

    No Known Activations