© 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. 39455
    Prev
    Next
    INDEX
    Explanations

    Nigerian place names and surnames

    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
    锉
    -1.70
    箩
    -1.61
     seçenek
    -1.49
    籥
    -1.48
     mutta
    -1.45
    elbow
    -1.45
    ⵎ
    -1.44
     אבל
    -1.43
     映
    -1.41
    Complications
    -1.40
    POSITIVE LOGITS
    </em>
    1.59
     lørdag
    1.50
     Yoruba
    1.38
    8
    1.38
    7
    1.34
    –
    1.34
    2
    1.34
     torsdag
    1.33
     $*$
    1.33
    The
    1.30
    Activations Density 0.006%

    No Known Activations