© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-65K
    4. 3967
    Prev
    Next
    INDEX
    Explanations

    lists and common words

    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_65k_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
    但我
    0.41
    但他
    0.40
    但是我
    0.36
     لكن
    0.35
     Nhưng
    0.34
     ngunit
    0.34
    但也
    0.31
    <unused46>
    0.31
     जिससे
    0.30
    ەد
    0.30
    POSITIVE LOGITS
     the
    0.54
    The
    0.50
    the
    0.49
     there
    0.47
     The
    0.47
     one
    0.40
     when
    0.39
     during
    0.38
     all
    0.37
    on
    0.37
    Activations Density 0.158%

    No Known Activations