© 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. 16-GEMMASCOPE-2-RES-262K
    7. 4318
    Prev
    Next
    INDEX
    Explanations

    word roots: negative, specific, or foreign

    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_16_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
     for
    1.83
     from
    1.43
    ן
    1.42
     on
    1.23
    ூர்
    1.21
     JFK
    1.20
     is
    1.13
     has
    1.10
     YMCA
    1.08
     FACS
    1.08
    POSITIVE LOGITS
    2
    1.92
    4
    1.68
    3
    1.58
    9
    1.56
    6
    1.52
    5
    1.47
    8
    1.46
    7
    1.41
    ت
    1.38
    س
    1.34
    Activations Density 0.291%

    No Known Activations