© 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. 31-GEMMASCOPE-2-RES-16K
    7. 14818
    Prev
    Next
    INDEX
    Explanations

    foreign characters, non-English words

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

    examples and explanations

    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_31_width_16k_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
    ');
    0.52
    status
    0.50
    ')->
    0.47
     outrageous
    0.46
    """
    0.45
    ']['
    0.45
    bsite
    0.44
    ();
    0.44
    ?
    0.44
    ="";
    0.44
    POSITIVE LOGITS
     rayonnement
    0.44
     soğ
    0.44
    εκ
    0.43
     ancor
    0.42
    變
    0.42
     oczy
    0.41
    ه‌
    0.41
    筏
    0.41
     झर
    0.41
    ोम
    0.41
    Activations Density 0.003%

    No Known Activations