© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 29-GEMMASCOPE-2-RES-65K
    7. 1928
    Prev
    Next
    INDEX
    Explanations

    code related to visualization and errors

    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
    Negative Logits
     DHCP
    0.69
     alternator
    0.60
    ્ષ
    0.59
     Jub
    0.59
     elektro
    0.59
     thailand
    0.59
     adsor
    0.59
     raid
    0.58
    💳
    0.58
     Mete
    0.58
    POSITIVE LOGITS
    LookAndFeelInfo
    0.45
    WarningLevel
    0.43
    UnifiedTopology
    0.42
    numberOf
    0.41
    originals
    0.41
     DefaultTargets
    0.40
    dataType
    0.40
    fontWeight
    0.39
    getCameraId
    0.39
    getResponseCode
    0.39
    Activations Density 0.628%

    No Known Activations