© 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. 22-GEMMASCOPE-RES-131K
    7. 71292
    Prev
    Next
    INDEX
    Explanations

    smart followed by common nouns

    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
    ↵
    -4.47
     praktisch
    -2.89
    皛
    -2.70
    </strong>
    -2.63
     
    -2.58
     technisch
    -2.41
    푉
    -2.31
    部分が
    -2.25
    カッコいい
    -2.25
    かっこ
    -2.20
    POSITIVE LOGITS
    In
    3.30
    ،
    2.88
    Like
    2.70
    Even
    2.66
    Some
    2.61
    Here
    2.61
    ة
    2.61
    All
    2.45
    Most
    2.44
    ],
    2.42
    Activations Density 0.009%

    No Known Activations