© 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. 22-GEMMASCOPE-RES-131K
    7. 14064
    Prev
    Next
    INDEX
    Explanations

    lack of prior experience

    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_22/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
    termilk
    -0.95
     dėl
    -0.90
     quello
    -0.90
     want
    -0.88
     Mote
    -0.86
    ckeye
    -0.85
     ブレスレット
    -0.85
    îtra
    -0.84
    nees
    -0.83
     flere
    -0.83
    POSITIVE LOGITS
     previously
    1.73
     previous
    1.59
     sebelumnya
    1.53
     zuvor
    1.42
     vorher
    1.42
     prior
    1.37
     préalable
    1.35
     except
    1.34
    此前
    1.23
    Previously
    1.20
    Activations Density 0.039%

    No Known Activations