© 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. 22-GEMMASCOPE-RES-131K
    4. 98594
    Prev
    Next
    INDEX
    Explanations

    scientific study

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

    citation and reference markers in academic and scientific 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_22/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
     to
    -0.96
     it
    -0.90
     diputados
    -0.88
     undertaking
    -0.88
    ёг
    -0.87
    momile
    -0.86
    raisemb
    -0.85
     something
    -0.84
    apri
    -0.84
     what
    -0.83
    POSITIVE LOGITS
    eting
    0.93
    ită
    0.91
     boomers
    0.88
     aigu
    0.85
    푼
    0.85
     capacités
    0.84
    IDTH
    0.84
     Guangdong
    0.84
    ismus
    0.82
    LAKE
    0.82
    Activations Density 0.004%

    No Known Activations