© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 49517
    Prev
    Next
    INDEX
    Explanations

    minimal residual

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    entious
    -0.73
    rect
    -0.72
    邹
    -0.72
     excru
    -0.71
     Blackwood
    -0.70
    λία
    -0.68
     sombre
    -0.68
     repaint
    -0.67
    antwoorden
    -0.67
    umpy
    -0.66
    POSITIVE LOGITS
     residual
    6.63
    Residual
    5.75
     Residual
    5.69
    residual
    5.66
     residuals
    5.38
     residue
    4.31
     RESID
    4.19
     resid
    4.13
     residues
    3.97
    resid
    3.80
    Activations Density 0.111%

    No Known Activations