© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 93139
    Prev
    Next
    INDEX
    Explanations

    punctuation and special characters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    يد
    0.56
    ᅪ
    0.50
    Déc
    0.49
    Classe
    0.48
    Conservative
    0.48
    Millions
    0.48
    DEPARTMENT
    0.47
    Espagne
    0.47
    L
    0.47
    氇
    0.47
    POSITIVE LOGITS
     బె
    0.47
     حدی
    0.46
    ිරි
    0.45
    ceil
    0.44
    ：（
    0.43
    ẵn
    0.42
    volvement
    0.41
    ikes
    0.41
    ,}
    0.41
    рен
    0.41
    Activations Density 0.000%

    No Known Activations