© 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. 17-GEMMASCOPE-2-RES-16K
    7. 504
    Prev
    Next
    INDEX
    Explanations

    learning_rate, socket, error

    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_17_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
     neue
    0.69
     nieuwe
    0.68
     S
    0.67
     new
    0.66
     R
    0.66
     J
    0.64
     O
    0.64
     I
    0.64
     yeni
    0.64
     novo
    0.63
    POSITIVE LOGITS
    ба
    0.71
    Де
    0.70
    iterations
    0.70
    Ба
    0.68
    houses
    0.67
    З
    0.66
    На
    0.65
    п
    0.65
    shifts
    0.64
    Ну
    0.64
    Activations Density 0.009%

    No Known Activations