© 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-262K
    7. 25292
    Prev
    Next
    INDEX
    Explanations

    present, followed by subject description

    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
    Corner
    0.22
    Global
    0.22
     leakage
    0.21
    ==
    0.21
    Config
    0.20
    (<
    0.20
    @
    0.20
    Parameter
    0.20
    Temporary
    0.19
     glare
    0.19
    POSITIVE LOGITS
     ਅਤੇ
    0.27
    ز
    0.27
     و
    0.26
     и
    0.25
     ۽
    0.25
     وس
    0.25
     bienes
    0.25
    और
    0.25
     és
    0.24
     और
    0.24
    Activations Density 0.000%

    No Known Activations