© 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. 4058
    Prev
    Next
    INDEX
    Explanations

    gene expression, mutations, isoforms

    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
     ballroom
    0.79
     uncont
    0.77
     banquet
    0.73
     custom
    0.68
    custom
    0.67
    request
    0.66
    Custom
    0.63
    <>(
    0.63
     request
    0.63
     agile
    0.62
    POSITIVE LOGITS
     expression
    1.47
     expressão
    1.32
    expression
    1.29
     Expression
    1.27
     upregulation
    1.24
     overexpression
    1.21
    Expression
    1.20
     expressions
    1.19
     Expressions
    1.19
     expresión
    1.19
    Activations Density 0.133%

    No Known Activations