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. 29-GEMMASCOPE-2-RES-65K
    4. 5600
    Prev
    Next
    INDEX
    Explanations

    small things

    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_29_width_65k_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
     शतक
    0.67
     đoán
    0.63
     ン
    0.61
    呻
    0.59
    ခံ
    0.58
    >[]
    0.58
    बत
    0.58
    vera
    0.57
    ≿
    0.56
    IELD
    0.56
    POSITIVE LOGITS
     small
    5.40
    Small
    5.01
     Small
    4.99
    small
    4.91
     smaller
    4.83
     tiny
    4.54
     Smaller
    4.48
     SMALL
    4.43
     pequeña
    4.41
    Smaller
    4.41
    Activations Density 1.795%

    No Known Activations