© 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. 17816
    Prev
    Next
    INDEX
    Explanations

    HTML entity `<`

    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
    ל
    1.35
    ल
    1.09
    ল
    1.02
    ک
    0.99
     a
    0.94
    ل
    0.93
    ن
    0.92
    对
    0.84
    ൽ
    0.83
    شر
    0.82
    POSITIVE LOGITS
    ında
    0.94
    ever
    0.80
    jų
    0.79
    í
    0.77
    ending
    0.76
    ə
    0.75
    ᱙
    0.75
    ando
    0.74
    jus
    0.74
    isjon
    0.72
    Activations Density 0.001%

    No Known Activations