© 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. 133606
    Prev
    Next
    INDEX
    Explanations

    special characters followed by words

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

    language analysis and structure

    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
     Boż
    0.38
     económ
    0.37
    飲
    0.37
     wilfully
    0.36
    لای
    0.36
     Bo
    0.36
     deliberately
    0.36
     chiefly
    0.35
    厉
    0.35
    柽
    0.35
    POSITIVE LOGITS
     voila
    0.45
    Favorites
    0.45
     interag
    0.42
    alumno
    0.41
    client
    0.41
     ain
    0.40
    妗
    0.40
     actuator
    0.39
    CategoryId
    0.39
     মোকাবেলা
    0.39
    Activations Density 0.002%

    No Known Activations