© 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. 6194
    Prev
    Next
    INDEX
    Explanations

    multilingual questions and commands

    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
    '
    1.37
    ’
    1.37
     a
    1.34
     that
    1.27
     or
    1.20
     is
    1.16
    లో
    1.13
    ع
    1.11
    ר
    1.09
    )’
    1.04
    POSITIVE LOGITS
    もら
    1.08
    在
    1.08
    بي
    0.99
     οποία
    0.99
     जिसके
    0.91
    في
    0.91
    و
    0.91
    ъ
    0.90
    ל
    0.89
     Actualmente
    0.88
    Activations Density 0.001%

    No Known Activations