© 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-262K
    7. 41940
    Prev
    Next
    INDEX
    Explanations

    burstiness and perplexity

    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
    藉
    0.47
     giường
    0.44
    ську
    0.43
    牀
    0.43
    ಲಭ
    0.43
    上半
    0.42
    opting
    0.42
    він
    0.42
    "。
    0.41
    BOUNDARY
    0.40
    POSITIVE LOGITS
    ăpadă
    0.49
     energi
    0.48
    lebn
    0.46
     Majorana
    0.46
     kom
    0.45
    妏
    0.45
     communism
    0.44
     വീഡിയോ
    0.44
     Kom
    0.44
     Leb
    0.44
    Activations Density 0.000%

    No Known Activations