© 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. 31-GEMMASCOPE-2-RES-65K
    7. 13340
    Prev
    Next
    INDEX
    Explanations

    list item specifiers

    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
     What
    0.49
    ."),
    0.43
     How
    0.41
     what
    0.39
     Bl
    0.39
     Assessment
    0.38
    ...">
    0.38
     Who
    0.37
    .").
    0.37
     history
    0.37
    POSITIVE LOGITS
    ：
    0.54
    ઃ
    0.52
    ៖
    0.51
    :‏
    0.50
    ?:
    0.48
    Cuando
    0.44
    Estos
    0.43
    ::
    0.43
    ։
    0.43
    ﹔
    0.42
    Activations Density 0.276%

    No Known Activations