© 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. 32111
    Prev
    Next
    INDEX
    Explanations

    setting text or title

    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
     preamp
    -0.85
    ների
    -0.84
    かというと
    -0.84
    wole
    -0.84
     öppna
    -0.84
     naturligt
    -0.83
    žnost
    -0.80
     malaise
    -0.79
    cassert
    -0.79
     imprensa
    -0.77
    POSITIVE LOGITS
    २
    0.82
    örung
    0.80
    ❼
    0.79
     ?></
    0.75
     acús
    0.74
     String
    0.73
    imbangan
    0.73
    quarelle
    0.72
    食欲
    0.72
    цвет
    0.71
    Activations Density 0.002%

    No Known Activations