© 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. 34-GEMMASCOPE-RES-131K
    7. 60840
    Prev
    Next
    INDEX
    Explanations

    good or great descriptions

    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_34/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
    ditional
    -1.10
    perature
    -1.05
    ceptable
    -1.03
     basados
    -1.02
    ramid
    -1.00
    KeyName
    -0.96
    vaila
    -0.95
     piede
    -0.95
     vinculados
    -0.94
    letras
    -0.89
    POSITIVE LOGITS
     a
    4.34
     good
    1.77
     хороший
    1.63
     an
    1.63
    是个
    1.49
     buena
    1.48
     buen
    1.45
    是個
    1.37
    Отлич
    1.28
     great
    1.27
    Activations Density 0.082%

    No Known Activations