© 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. 22-GEMMASCOPE-RES-131K
    7. 14736
    Prev
    Next
    INDEX
    Explanations

    descriptive adjectives with strong connotations

    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
     all
    -2.45
     because
    -2.44
     two
    -2.16
     furthering
    -2.13
     very
    -2.11
     extraordinarily
    -2.09
     from
    -2.08
     gets
    -2.08
     with
    -2.06
     nestled
    -2.06
    POSITIVE LOGITS
     strikingly
    2.08
     ludicrous
    1.93
     boister
    1.91
     captivating
    1.91
     momentous
    1.87
     startling
    1.85
     secluded
    1.81
     wondrous
    1.81
     delightfully
    1.81
     alluring
    1.80
    Activations Density 0.022%

    No Known Activations