© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 104591
    Prev
    Next
    INDEX
    Explanations

    contradicts or impossible situations

    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
     feels
    -0.85
     forbearance
    -0.83
    Jeśli
    -0.83
    ovala
    -0.79
    增加
    -0.79
    也要
    -0.79
     talvez
    -0.77
     wieś
    -0.77
     also
    -0.77
     like
    -0.77
    POSITIVE LOGITS
     impossibility
    1.34
     impossible
    1.26
    impossible
    1.16
    不可能
    1.05
    impos
    1.04
    Impossible
    1.02
     Impossible
    0.95
     contradicts
    0.94
    Clearly
    0.93
    obviously
    0.92
    Activations Density 0.070%

    No Known Activations