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. 978
    Prev
    Next
    INDEX
    Explanations

    inclusive, integer, unique, far

    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
     cárc
    0.48
    ຽ
    0.47
    axie
    0.46
     wzrost
    0.45
    scopic
    0.45
    aphthal
    0.45
     pretext
    0.44
    țională
    0.44
    pouring
    0.44
     amenazas
    0.44
    POSITIVE LOGITS
     Import
    0.55
    O
    0.54
    AC
    0.52
    import
    0.50
    在
    0.49
     Importing
    0.48
     Hurricane
    0.47
     and
    0.47
     ou
    0.46
    ']
    0.46
    Activations Density 0.001%

    No Known Activations