© 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. 3799
    Prev
    Next
    INDEX
    Explanations

    hexadecimal strings and identifiers

    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
    r
    2.03
    b
    1.83
    y
    1.77
    s
    1.77
    m
    1.76
    l
    1.76
    t
    1.75
    e
    1.71
    i
    1.67
    d
    1.65
    POSITIVE LOGITS
     standard
    0.69
     OBS
    0.69
     daily
    0.68
     Standard
    0.67
     regulatory
    0.65
     DRM
    0.65
     Regulatory
    0.64
     PLA
    0.63
     Source
    0.63
     sources
    0.62
    Activations Density 0.035%

    No Known Activations