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. 2542
    Prev
    Next
    INDEX
    Explanations

    Spanish noun compounds

    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
    при
    0.69
    して
    0.67
    ть
    0.66
     нее
    0.66
    ком
    0.63
    か
    0.62
     по
    0.62
    н
    0.62
    ього
    0.62
    き
    0.61
    POSITIVE LOGITS
     astral
    1.01
     dental
    1.00
     ceramic
    1.00
     samochod
    1.00
     های
    0.98
     floral
    0.98
     kimia
    0.97
     sosial
    0.96
     funer
    0.96
     geological
    0.95
    Activations Density 0.155%

    No Known Activations