© 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. 129207
    Prev
    Next
    INDEX
    Explanations

    causal explanations

    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
    澌
    -1.02
    んですけど
    -1.00
    ♢
    -0.99
     ogen
    -0.96
    Поэтому
    -0.96
    机的
    -0.96
     consultato
    -0.96
    issez
    -0.95
    glades
    -0.94
     SRT
    -0.93
    POSITIVE LOGITS
     because
    2.00
     there
    1.45
    because
    1.38
    因为
    1.37
    因為
    1.34
     porque
    1.26
     you
    1.23
     they
    1.18
     your
    1.15
     karena
    1.15
    Activations Density 0.012%

    No Known Activations