© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 88886
    Prev
    Next
    INDEX
    Explanations

    third party

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

    compound nouns and technical terms

    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_262k_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
     tổ
    0.55
     phổ
    0.54
     cả
    0.53
     règle
    0.51
     bột
    0.50
     ं
    0.50
     फैलता
    0.50
     पुर
    0.50
     আসিল
    0.49
     ءِ
    0.49
    POSITIVE LOGITS
     validators
    0.41
     December
    0.41
    November
    0.41
     endpoints
    0.40
    verz
    0.39
    Instagram
    0.39
     figlio
    0.39
     January
    0.38
    in
    0.38
     tag
    0.38
    Activations Density 0.000%

    No Known Activations