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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 129850
    Prev
    Next
    INDEX
    Explanations

    long-term or recurring conditions

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

    words with the suffix '-ally', particularly in terms like 'chronically', 'perennially', and 'habitually'.

    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
     transitioned
    -1.52
     of
    -1.49
    </em>
    -1.47
    皞
    -1.39
    
    -1.37
     потом
    -1.35
    CARACTERIST
    -1.34
     umfass
    -1.31
    
    -1.31
    雠
    -1.30
    POSITIVE LOGITS
    in
    1.45
    的问题
    1.41
    早上
    1.39
    ↵
    1.38
     olarak
    1.33
     zult
    1.32
     nello
    1.31
    rozco
    1.30
    沒有
    1.30
     tienen
    1.29
    Activations Density 0.064%

    No Known Activations