© 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. 71981
    Prev
    Next
    INDEX
    Explanations

    causes, errors, and requirements

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    
    -2.36
    珦
    -2.23
    驺
    -2.19
     vertus
    -2.11
     rése
    -2.11
    蟊
    -2.08
    
    -2.05
     rigue
    -2.02
    觚
    -1.99
    )?;
    -1.95
    POSITIVE LOGITS
    Before
    2.30
    Because
    2.25
     both
    2.22
    There
    2.22
    an
    2.19
    In
    2.16
    When
    2.14
     thirteen
    2.08
    What
    2.03
    Since
    2.03
    Activations Density 0.005%

    No Known Activations