© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 112772
    Prev
    Next
    INDEX
    Explanations

    acronyms in parentheses

    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
    
    -2.09
    ⛦
    -2.05
     ilustraciones
    -2.02
     vedea
    -1.95
    莅
    -1.95
    Kullan
    -1.91
     rád
    -1.89
     traducciones
    -1.88
    رحلة
    -1.87
    𖤣
    -1.86
    POSITIVE LOGITS
    e
    2.30
    such
    2.22
    of
    1.95
    }
    1.88
    </b>
    1.88
    s
    1.76
    us
    1.70
     キャプ
    1.66
    other
    1.64
    and
    1.61
    Activations Density 0.112%

    No Known Activations