© 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. 22-GEMMASCOPE-RES-131K
    7. 65480
    Prev
    Next
    INDEX
    Explanations

    well known in the art

    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
    regarding
    -1.09
    Į
    -1.08
    さぁ
    -0.99
    ówczas
    -0.97
     indicó
    -0.96
     dziecię
    -0.96
    えっ
    -0.95
    になるので
    -0.94
    にします
    -0.93
    pherds
    -0.92
    POSITIVE LOGITS
     has
    1.20
     in
    0.90
    航班
    0.87
     المثال
    0.84
     was
    0.84
     at
    0.82
     whose
    0.82
    烽
    0.81
    lery
    0.81
    rån
    0.81
    Activations Density 0.175%

    No Known Activations