© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-65K
    4. 28039
    Prev
    Next
    INDEX
    Explanations

    macro and argument

    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
    ffiti
    0.54
    STRAINT
    0.52
    قلال
    0.43
    IDUAL
    0.42
    𝚂
    0.42
     ಕೆಲವು
    0.42
    sax
    0.41
    ﻤ
    0.40
    リート
    0.40
    formen
    0.40
    POSITIVE LOGITS
     effortlessly
    0.49
     about
    0.47
     Suriname
    0.45
     flattered
    0.43
     iOS
    0.42
     short
    0.42
     WhatsApp
    0.41
     unwavering
    0.41
     incessantly
    0.40
    IOException
    0.40
    Activations Density 0.011%

    No Known Activations