© 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. 10-GEMMASCOPE-RES-131K
    7. 60145
    Prev
    Next
    INDEX
    Explanations

    conventionally, prior art

    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
     of
    -2.17
     is
    -1.59
     etc
    -1.41
     up
    -1.34
     U
    -1.32
    共同
    -1.32
     aka
    -1.31
     сегодня
    -1.30
    多く
    -1.30
     t
    -1.29
    POSITIVE LOGITS
     vín
    1.49
     motoru
    1.48
    mby
    1.38
     kompres
    1.38
    aviation
    1.36
    鵟
    1.35
     jonge
    1.35
     oxu
    1.34
    ąp
    1.34
     indiví
    1.34
    Activations Density 0.172%

    No Known Activations