© 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-262K
    4. 12942
    Prev
    Next
    INDEX
    Explanations

    shows all the details

    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
     Accuracy
    0.46
    Գ
    0.46
     Ancient
    0.45
    నె
    0.44
    信仰
    0.43
     Fate
    0.43
    友情
    0.42
    ГА
    0.42
    机
    0.42
     accuracy
    0.41
    POSITIVE LOGITS
    was
    0.55
     was
    0.51
     טי
    0.49
    the
    0.47
    ò
    0.46
    으로
    0.44
    has
    0.43
     supermerc
    0.43
     dusting
    0.43
    should
    0.42
    Activations Density 0.001%

    No Known Activations