© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 123721
    Prev
    Next
    INDEX
    Explanations

    2D

    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
     Saltar
    -2.50
    }$
    -2.25
    )”.
    -2.02
    ;");
    -1.91
     sū
    -1.89
    涠
    -1.88
     Comprometido
    -1.87
    ቍ
    -1.87
     diser
    -1.82
     vitale
    -1.82
    POSITIVE LOGITS
    厹
    2.36
     –
    2.16
     
    1.95
    </strong>
    1.91
     และ
    1.88
     прошлого
    1.86
    '
    1.86
     แต่
    1.85
     большая
    1.84
     больших
    1.82
    Activations Density 0.009%

    No Known Activations