© 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. 93313
    Prev
    Next
    INDEX
    Explanations

    in practice

    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
     uppdater
    -0.86
    hihi
    -0.79
    XmlIgnore
    -0.76
    Intermediate
    -0.76
    ℴ
    -0.75
     Fiche
    -0.74
     معلومات
    -0.74
    Salida
    -0.73
    intermediate
    -0.73
     isole
    -0.73
    POSITIVE LOGITS
     start
    1.90
     Start
    1.55
     beginning
    1.46
    Start
    1.38
    start
    1.38
     end
    1.36
     starts
    1.27
     begin
    1.23
     baseline
    1.20
     starting
    1.19
    Activations Density 0.005%

    No Known Activations