© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-65K
    7. 5010
    Prev
    Next
    INDEX
    Explanations

    hello world code

    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_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
    (“
    0.79
    Under
    0.76
    "]]
    0.73
    ileg
    0.72
     (“
    0.71
    Ша
    0.71
    Based
    0.70
    zył
    0.70
    “
    0.69
    Под
    0.69
    POSITIVE LOGITS
     logout
    1.12
     login
    1.09
     Toggle
    1.03
     email
    1.02
     toggle
    1.01
     Logo
    0.98
    logout
    0.97
     Logout
    0.96
     logo
    0.96
     calendar
    0.95
    Activations Density 0.042%

    No Known Activations