© 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. 129574
    Prev
    Next
    INDEX
    Explanations

    dealing with

    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
     kompatibel
    -1.14
     konfig
    -1.12
    :{},
    -1.03
     kompati
    -1.01
     praktik
    -0.98
     defekt
    -0.98
    这个
    -0.97
     aussit
    -0.97
     特写
    -0.96
     pérd
    -0.94
    POSITIVE LOGITS
     ebenfalls
    1.17
    同じく
    1.10
     also
    1.05
    ਘ
    1.04
     tiež
    1.02
    ਠ
    0.99
     розовый
    0.98
    するもの
    0.97
    することも
    0.96
     thier
    0.96
    Activations Density 0.075%

    No Known Activations