© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 57417
    Prev
    Next
    INDEX
    Explanations

    lambda expressions, code blocks

    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
    igheid
    -0.86
    ਜ
    -0.82
    бурга
    -0.78
     schonmal
    -0.78
    сно
    -0.78
     ambayo
    -0.77
    vdots
    -0.75
    stellungen
    -0.74
     confiar
    -0.73
    ًا
    -0.72
    POSITIVE LOGITS
    )->
    1.03
    ")){
    0.91
     =>
    
    0.89
    ankt
    0.87
     posible
    0.84
     ->
    0.84
    })->
    0.83
     tional
    0.81
     tradisional
    0.79
     סט
    0.79
    Activations Density 0.009%

    No Known Activations