Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 22-GEMMASCOPE-2-RES-16K
    4. 9250
    Prev
    Next
    INDEX
    Explanations

    consonant clusters and punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_22_width_16k_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
    
    1.34
    squre
    1.31
    Acetic
    1.30
    orems
    1.28
    เชสเตอร์
    1.28
     ServicePolicy
    1.28
    ន្
    1.27
    ímetros
    1.24
    queous
    1.24
    ometro
    1.23
    POSITIVE LOGITS
     as
    1.08
     "
    1.06
     at
    1.06
     in
    1.02
    ↵
    1.00
     on
    0.98
     from
    0.97
     '
    0.95
    ↵↵
    0.94
     or
    0.87
    Activations Density 0.148%

    No Known Activations