Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 43678
    Prev
    Next
    INDEX
    Explanations

    foreign language characters

    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
    orough
    0.53
    <unused60>
    0.52
     m
    0.51
     described
    0.50
     dalam
    0.50
     as
    0.47
     d
    0.46
     hearing
    0.46
     self
    0.45
     II
    0.45
    POSITIVE LOGITS
    އ
    0.55
    م
    0.49
    بار
    0.48
    ИА
    0.48
    친
    0.47
    ιος
    0.47
    αν
    0.47
    бин
    0.46
     Annotation
    0.46
    ຜະລິດຕະພັນ
    0.46
    Activations Density 0.000%

    No Known Activations