© 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. 182859
    Prev
    Next
    INDEX
    Explanations

    specific word transitions

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

    but contrasts, manifest, helps

    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
     mực
    0.49
    黙
    0.48
    SENT
    0.47
     क्लब
    0.46
    txt
    0.46
     INDEX
    0.46
    ట్లా
    0.45
     SENT
    0.45
    쌩
    0.44
     SURVEY
    0.44
    POSITIVE LOGITS
    ور
    0.55
    reated
    0.43
    Macros
    0.43
    Concini
    0.42
    غذ
    0.42
    Wer
    0.42
     specialties
    0.42
    Ferr
    0.41
     Willow
    0.41
     especializados
    0.41
    Activations Density 0.000%

    No Known Activations