© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 13852
    Prev
    Next
    INDEX
    Explanations

    this followed by punctuation

    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
    es
    -1.61
    i
    -1.59
    }$
    -1.48
     staggering
    -1.48
    );
    -1.46
     öff
    -1.44
    龊
    -1.35
     seems
    -1.31
    蒜
    -1.31
    if
    -1.26
    POSITIVE LOGITS
    zestaw
    1.94
    źródło
    1.55
    cursions
    1.52
    verter
    1.52
    Czytaj
    1.51
    詬
    1.50
    
    1.49
    Կ
    1.45
    nå
    1.45
    esség
    1.45
    Activations Density 0.025%

    No Known Activations