© 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. 22-GEMMASCOPE-RES-131K
    7. 128130
    Prev
    Next
    INDEX
    Explanations

    simple method or concept

    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
    糁
    -1.21
    Spolja
    -1.16
     anden
    -1.14
    ㈲
    -1.12
    郢
    -1.12
    spania
    -1.10
     起毛
    -1.09
    ῞
    -1.08
    likopter
    -1.07
     contraire
    -1.06
    POSITIVE LOGITS
     simple
    1.91
    simple
    1.62
     sederhana
    1.52
    Simple
    1.46
     Simple
    1.45
    简单的
    1.31
     easy
    1.30
     простой
    1.27
     but
    1.24
     ساده
    1.20
    Activations Density 0.082%

    No Known Activations