© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 39146
    Prev
    Next
    INDEX
    Explanations

    phonological / phonology

    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
    “
    -3.20
    s
    -3.02
    which
    -2.75
    where
    -2.72
    ”
    -2.39
     perde
    -2.34
    謦
    -2.23
    }
    -2.19
    焿
    -2.19
    +};
    -2.14
    POSITIVE LOGITS
    </strong>
    2.39
    氿
    2.30
     exitos
    2.25
     
    2.11
     применя
    2.09
    ökning
    2.09
    が良い
    2.05
     partag
    2.05
    );
    2.03
    :-
    2.02
    Activations Density 0.004%

    No Known Activations