© 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. 65994
    Prev
    Next
    INDEX
    Explanations

    broken or failing states

    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
     wondrous
    -2.00
     การ
    -1.80
     bizarre
    -1.78
     quintessential
    -1.77
     
    -1.77
    perhaps
    -1.74
     momentous
    -1.74
     delightfully
    -1.71
     shimmering
    -1.70
     gigantic
    -1.70
    POSITIVE LOGITS
     and
    2.17
     EVERY
    2.17
     or
    2.16
     your
    2.16
     our
    2.13
     every
    2.13
     one
    2.09
     all
    2.09
     both
    2.05
     multifaceted
    2.00
    Activations Density 0.092%

    No Known Activations