© 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. 45407
    Prev
    Next
    INDEX
    Explanations

    review HP

    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
    も同じ
    -1.58
     valori
    -1.44
     creat
    -1.41
     ovviamente
    -1.38
    
    -1.38
     geene
    -1.35
    ervant
    -1.35
    饜
    -1.34
     manutenção
    -1.33
    </b>
    -1.30
    POSITIVE LOGITS
     for
    1.81
     we
    1.70
     with
    1.64
     will
    1.58
     With
    1.54
     What
    1.52
     radically
    1.51
     really
    1.49
     Ultimately
    1.49
     helps
    1.48
    Activations Density 0.283%

    No Known Activations