© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 29-GEMMASCOPE-2-RES-65K
    7. 4397
    Prev
    Next
    INDEX
    Explanations

    equations involving x

    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
    θν
    0.78
    Hence
    0.77
     múlti
    0.75
     monotonically
    0.75
     Denote
    0.74
    Denote
    0.73
    Suppose
    0.73
    ẏ
    0.72
    üglich
    0.72
    _{+}
    0.71
    POSITIVE LOGITS
     scrubs
    0.72
     undeveloped
    0.61
     cheered
    0.60
     Teri
    0.59
     Canaan
    0.59
     dystopian
    0.58
    chec
    0.56
     libra
    0.56
     puppies
    0.56
     librarian
    0.56
    Activations Density 0.208%

    No Known Activations