© 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. 79114
    Prev
    Next
    INDEX
    Explanations

    android layout attributes

    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
    borgen
    -0.85
     WaitForSeconds
    -0.84
    ühungen
    -0.82
    akti
    -0.79
    Carb
    -0.77
    ingar
    -0.73
     Familien
    -0.72
    ို
    -0.72
    ableView
    -0.72
     Vorbe
    -0.71
    POSITIVE LOGITS
     Maurer
    0.82
    adna
    0.82
    LLE
    0.80
     Dependence
    0.78
    Attach
    0.76
     centre
    0.76
     Fabulous
    0.75
    dependence
    0.75
     depended
    0.74
     fabulous
    0.74
    Activations Density 0.007%

    No Known Activations