© 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. 20022
    Prev
    Next
    INDEX
    Explanations

    reading lines or matching text

    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
    ség
    1.36
    ني
    1.29
    siz
    1.28
    s
    1.24
    কে
    1.23
    ের
    1.21
    sı
    1.17
    يز
    1.13
    是
    1.13
    larda
    1.12
    POSITIVE LOGITS
    ing
    1.38
    ,
    1.34
    an
    1.29
    おしゃれ
    1.21
    お客
    1.18
    お金
    1.16
    ia
    1.15
    il
    1.10
    el
    1.05
    us
    1.04
    Activations Density 0.005%

    No Known Activations