© 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. 12205
    Prev
    Next
    INDEX
    Explanations

    highly + descriptive adjective

    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
     delightfully
    -2.50
    </i>
    -2.38
    addCriterion
    -2.28
    静静
    -2.25
    ፨
    -2.19
    тися
    -2.19
    ⬈
    -2.13
     поскольку
    -2.09
     eminently
    -2.09
     otras
    -2.08
    POSITIVE LOGITS
    </h2>
    3.39
    there
    3.09
    re
    2.81
    Following
    2.78
    Very
    2.78
    出来た
    2.75
    Some
    2.72
    話は
    2.64
    Several
    2.64
    ،
    2.53
    Activations Density 0.021%

    No Known Activations