© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 15548
    Prev
    Next
    INDEX
    Explanations

    afferent nerve fibers

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

    suffixes of words, particularly those ending with 'ent', 'ing', 'ment', and 'ender'.

    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
    ’
    -2.61
    </i>
    -2.38
    );
    -2.31
    ]));
    -2.30
    o
    -2.22
    ;
    -2.16
     be
    -2.08
    🌞
    -2.08
    __":
    -2.06
    
    -2.05
    POSITIVE LOGITS
    簠
    2.25
    一来
    2.23
     accruing
    2.14
    他知道
    2.00
    他要
    2.00
     THERE
    1.98
    谖
    1.98
    他对
    1.96
    ↵↵
    1.94
    えている
    1.91
    Activations Density 0.007%

    No Known Activations