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. 350
    Prev
    Next
    INDEX
    Explanations

    markdown table structure

    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
    ,
    0.96
     s
    0.95
     a
    0.94
     in
    0.93
     e
    0.93
     an
    0.91
     not
    0.89
     all
    0.88
     un
    0.86
     to
    0.85
    POSITIVE LOGITS
    Usuario
    1.60
    Tipo
    1.47
    geschossiges
    1.46
    Cadastro
    1.45
    hôpital
    1.41
    
    1.39
    Aluno
    1.38
    Usuarios
    1.37
    количество
    1.35
    ayvachi
    1.35
    Activations Density 0.565%

    No Known Activations