© 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. 10-GEMMASCOPE-RES-131K
    7. 74895
    Prev
    Next
    INDEX
    Explanations

    astounding descriptions

    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_10/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
    Several
    -2.36
    Even
    -2.34
    There
    -2.31
     more
    -2.25
    When
    -2.25
    Some
    -2.22
    After
    -2.22
     any
    -2.16
     with
    -2.13
    With
    -2.09
    POSITIVE LOGITS
     ornate
    1.90
     vijf
    1.84
     delightfully
    1.84
     astounding
    1.83
     ludicrous
    1.83
     alluring
    1.81
     insane
    1.80
     insanely
    1.80
     famed
    1.80
    ౭
    1.78
    Activations Density 0.115%

    No Known Activations