© 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-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 8456
    Prev
    Next
    INDEX
    Explanations

    wild and related compounds

    np_acts-logits-general · gemini-2.5-flash-lite

    wild 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-2-27b-pt/resid_post/layer_53_width_65k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    屣
    0.44
    aitan
    0.44
    ATER
    0.42
    繇
    0.41
    闰
    0.40
    دید
    0.40
    publique
    0.39
    ிறது
    0.39
     Normalized
    0.38
    関節
    0.38
    POSITIVE LOGITS
     wild
    1.44
    wild
    1.19
     wilde
    1.13
     Wild
    1.11
    Wild
    1.10
     WILD
    1.09
    野
    1.07
     जंगली
    1.00
     sauvage
    0.92
     wildcard
    0.91
    Activations Density 0.018%

    No Known Activations