© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 998
    Prev
    Next
    INDEX
    Explanations

    strikingly

    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
     where
    -2.22
     when
    -2.14
     for
    -2.14
     all
    -2.05
     and
    -1.99
     because
    -1.91
     which
    -1.83
    r
    -1.80
     only
    -1.79
    z
    -1.77
    POSITIVE LOGITS
     insanely
    2.08
     alumno
    1.88
     exceedingly
    1.86
     REALLY
    1.85
     deliciously
    1.84
     decidedly
    1.82
     Ensuring
    1.78
     delightfully
    1.78
     quintessential
    1.78
     strikingly
    1.77
    Activations Density 0.011%

    No Known Activations