© 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. 129824
    Prev
    Next
    INDEX
    Explanations

    numpy as np

    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
    ですが
    -2.58
    ’,
    -2.27
     Hinsicht
    -2.16
    ’.
    -2.16
    がありますが
    -2.13
    って思
    -2.08
     Fassung
    -2.03
     daugiau
    -2.02
    があり
    -2.00
    ですか
    -2.00
    POSITIVE LOGITS
    /
    2.03
    不太
    2.02
    聽
    1.96
    те
    1.95
    읗
    1.94
     встреча
    1.85
     для
    1.83
    “
    1.81
     ism
    1.80
    ときは
    1.79
    Activations Density 0.002%

    No Known Activations