© 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. 123398
    Prev
    Next
    INDEX
    Explanations

    emoji and symbolism

    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
     フレ
    0.59
     Schwer
    0.50
     zwe
    0.47
     ක්
    0.46
     image
    0.46
     });
    0.46
     bevest
    0.46
     பெ
    0.46
     recommend
    0.45
     understand
    0.45
    POSITIVE LOGITS
    ب
    0.46
     değişik
    0.46
    Guides
    0.46
    حدى
    0.46
     aritmética
    0.45
    скім
    0.44
    س
    0.44
    اؤن
    0.43
    elses
    0.43
    𝐚
    0.43
    Activations Density 0.000%

    No Known Activations