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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 7749
    Prev
    Next
    INDEX
    Explanations

    code snippets and programming constructs

    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_65k_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
     Video
    0.45
     vidéo
    0.43
     video
    0.43
    ↵↵↵↵
    0.42
    é
    0.41
     multimedia
    0.41
    ência
    0.40
    í
    0.38
     जानिए
    0.38
     हमारा
    0.38
    POSITIVE LOGITS
     pitt
    0.41
    TAIN
    0.41
     кілько
    0.40
    LLING
    0.39
    PSON
    0.38
     روی
    0.38
    IVEN
    0.38
    Phr
    0.37
    +](=
    0.36
    Ể
    0.36
    Activations Density 0.054%

    No Known Activations