© 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. 34-GEMMASCOPE-RES-131K
    7. 59430
    Prev
    Next
    INDEX
    Explanations

    Rust error expectations, code, and topics

    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
     organizado
    -0.83
     warranty
    -0.79
    oje
    -0.79
     μαζί
    -0.78
    tahan
    -0.78
    osex
    -0.78
     бо
    -0.76
    getShared
    -0.76
     ulong
    -0.75
    quinta
    -0.75
    POSITIVE LOGITS
     as
    1.43
    flüge
    1.00
    דות
    0.81
    遶
    0.79
    particularly
    0.77
     importants
    0.77
    important
    0.77
     ladite
    0.76
    applicable
    0.75
    听着
    0.74
    Activations Density 0.006%

    No Known Activations