© 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. 117214
    Prev
    Next
    INDEX
    Explanations

    Askey-Wilson polynomials

    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
    Assign
    -0.70
     invertible
    -0.70
     ન
    -0.69
     tors
    -0.69
    ְב
    -0.68
    Decisions
    -0.68
     склады
    -0.67
    Hypothesis
    -0.66
     track
    -0.65
    зяй
    -0.65
    POSITIVE LOGITS
     orth
    1.16
     recurrence
    1.08
     Recur
    0.96
     Orth
    0.91
     moments
    0.89
     Rodrigues
    0.88
    acas
    0.85
    idist
    0.83
     Che
    0.82
     ALP
    0.81
    Activations Density 0.031%

    No Known Activations