© 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. 17624
    Prev
    Next
    INDEX
    Explanations

    code punctuation

    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
    یل
    1.55
    این
    1.29
    ről
    1.16
    feb
    1.16
    titor
    1.09
    a
    1.09
    s
    1.09
    timestamp
    1.08
    ा
    1.08
    inę
    1.07
    POSITIVE LOGITS
    на
    1.47
    ल
    1.33
    ل
    1.31
    é
    1.27
    يد
    1.24
    ల
    1.24
    ти
    1.22
    લ
    1.21
    is
    1.20
    у
    1.20
    Activations Density 0.232%

    No Known Activations