© 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. 34-GEMMASCOPE-RES-131K
    7. 845
    Prev
    Next
    INDEX
    Explanations

    existential quantifier

    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_34/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
     against
    -1.34
    fieur
    -0.89
    식
    -0.82
    Against
    -0.77
     because
    -0.76
     против
    -0.75
    kkue
    -0.75
     by
    -0.71
     END
    -0.71
     melawan
    -0.70
    POSITIVE LOGITS
     quantified
    1.70
     quantification
    1.70
     quanti
    1.67
     quantify
    1.60
    quanti
    1.56
    Quanti
    1.54
     Quanti
    1.51
     Quantification
    1.32
     QUANT
    1.29
    Quantification
    1.25
    Activations Density 0.033%

    No Known Activations