© 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. 16-GEMMASCOPE-2-RES-262K
    7. 4510
    Prev
    Next
    INDEX
    Explanations

    spell out or spell check

    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_16_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
    ه
    1.64
    a
    1.52
    ت
    1.50
    ي
    1.27
    f
    1.24
    י
    1.21
    larına
    1.13
    i
    1.13
    ले
    1.11
    ف
    1.11
    POSITIVE LOGITS
     spelling
    1.03
    Spell
    1.02
     Spell
    0.94
     Spelling
    0.91
     spell
    0.89
     학
    0.84
    ות
    0.83
     spells
    0.81
     attribu
    0.81
    getName
    0.78
    Activations Density 0.006%

    No Known Activations