© 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. 10-GEMMASCOPE-RES-131K
    7. 67888
    Prev
    Next
    INDEX
    Explanations

    temporal and conditional phrasing

    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_10/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
     schnellen
    -1.78
     speziellen
    -1.75
     sicheren
    -1.63
    }
    -1.63
     leichten
    -1.59
     besonderen
    -1.59
     vollständ
    -1.56
     pokud
    -1.50
    ”(
    -1.48
     leistungs
    -1.48
    POSITIVE LOGITS
     you
    1.84
    ians
    1.58
     we
    1.57
    EST
    1.47
    secta
    1.45
     he
    1.39
    fatter
    1.38
     perspek
    1.36
    formatics
    1.36
    ettes
    1.36
    Activations Density 0.020%

    No Known Activations