© 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-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-16K
    7. 10188
    Prev
    Next
    INDEX
    Explanations

    property name and type definitions

    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
    édon
    0.75
     biomark
    0.74
    宦
    0.71
     Cadastro
    0.71
     defaulted
    0.70
     AutoML
    0.70
    oléon
    0.70
     candidature
    0.68
     flagged
    0.68
     delinqu
    0.68
    POSITIVE LOGITS
    дня
    0.76
    ото
    0.74
     перед
    0.72
    interference
    0.71
    छ
    0.71
    min
    0.70
    мага
    0.69
     przed
    0.68
    辋
    0.67
    하자
    0.67
    Activations Density 0.066%

    No Known Activations