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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 29-GEMMASCOPE-2-RES-65K
    7. 2713
    Prev
    Next
    INDEX
    Explanations

    code structure symbols

    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_29_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
    anish
    0.79
     }
    0.77
     deterministic
    0.75
     reinforce
    0.72
     ha
    0.71
     Angriff
    0.71
     onion
    0.69
     Side
    0.68
     Without
    0.68
     ghost
    0.68
    POSITIVE LOGITS
    (
    0.74
    └
    0.72
    {
    0.71
    └──
    0.69
    ([
    0.69
    &&
    0.66
    ((
    0.66
    accordo
    0.64
    (((
    0.63
    ברת
    0.63
    Activations Density 0.020%

    No Known Activations