© 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. 40-GEMMASCOPE-2-RES-262K
    7. 942
    Prev
    Next
    INDEX
    Explanations

    mathematical formulas and numbers

    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_40_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
     lè
    0.41
    욬
    0.37
     इजीली
    0.36
    ropy
    0.36
    راث
    0.36
    丁目
    0.35
    传媒
    0.35
    وڈ
    0.35
    जेश
    0.35
    طلب
    0.34
    POSITIVE LOGITS
     seven
    0.48
    6
    0.46
     six
    0.45
     Sixty
    0.44
     छह
    0.42
     sixty
    0.41
     sechs
    0.38
     passage
    0.38
    passage
    0.38
     Seven
    0.38
    Activations Density 0.006%

    No Known Activations