© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 47416
    Prev
    Next
    INDEX
    Explanations

    parsing text to numbers

    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
    ینگ
    -0.85
    などを
    -0.84
    など
    -0.80
    :
    -0.78
     schéma
    -0.78
    ساء
    -0.77
    wą
    -0.76
     arbre
    -0.73
    ducts
    -0.73
     ثم
    -0.73
    POSITIVE LOGITS
     gevallen
    0.92
    范
    0.85
    liato
    0.85
     kleding
    0.83
     angebra
    0.83
     Try
    0.82
     $-.
    0.81
     drenched
    0.81
    Sortie
    0.81
     similaire
    0.80
    Activations Density 0.003%

    No Known Activations