© 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-3-1B
    5. 22-GEMMASCOPE-2-RES-16K
    7. 507
    Prev
    Next
    INDEX
    Explanations

    falar português

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_22_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     somewhat
    1.43
     reasonably
    1.37
     wary
    1.37
     reasonable
    1.36
     achieving
    1.34
     aboriginal
    1.33
     granted
    1.32
     부
    1.28
     designated
    1.26
     relatively
    1.26
    POSITIVE LOGITS
     fazendo
    2.88
     pessoas
    2.86
     quantidade
    2.85
     possui
    2.79
     não
    2.79
     fazer
    2.79
     também
    2.70
     apresenta
    2.70
     Não
    2.67
     vários
    2.64
    Activations Density 0.140%

    No Known Activations