© 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. 34-GEMMASCOPE-RES-131K
    7. 48619
    Prev
    Next
    INDEX
    Explanations

    disqualify or ineligible

    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
     may
    -1.16
    dila
    -0.79
    λευ
    -0.73
     stagnation
    -0.72
     repressed
    -0.71
    ucket
    -0.71
     NotImplemented
    -0.71
     lipos
    -0.71
     może
    -0.69
    Decre
    -0.68
    POSITIVE LOGITS
     disqual
    3.75
     disqualified
    3.69
     DQ
    1.82
     ineligible
    1.80
     eligibility
    1.68
    qualification
    1.68
     qualification
    1.48
     exclusion
    1.43
     qualifications
    1.38
    QUAL
    1.35
    Activations Density 0.034%

    No Known Activations