© 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. 67031
    Prev
    Next
    INDEX
    Explanations

    inherent flaws and indifference

    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
     these
    -1.24
     both
    -1.17
     should
    -1.05
     there
    -1.01
    when
    -0.98
     has
    -0.95
    稱為
    -0.94
    öpfer
    -0.92
    there
    -0.90
    嗎
    -0.90
    POSITIVE LOGITS
     insistence
    1.39
     being
    1.32
     inability
    1.31
    actéristi
    1.30
     BEING
    1.28
    shin
    1.27
    lenen
    1.26
     resultant
    1.24
     unwillingness
    1.16
     toujours
    1.16
    Activations Density 0.047%

    No Known Activations