© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 47670
    Prev
    Next
    INDEX
    Explanations

    SQLite database helper

    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
     calitate
    -0.76
    mods
    -0.68
    beams
    -0.67
    Προ
    -0.66
     Makes
    -0.65
     Rossa
    -0.63
    æus
    -0.63
     крити
    -0.63
    breviated
    -0.61
    ẻo
    -0.61
    POSITIVE LOGITS
     helper
    1.75
    helper
    1.57
    Helper
    1.48
     helpers
    1.45
     helping
    1.38
    OpenHelper
    1.31
     Helper
    1.30
     help
    1.27
    helpers
    1.23
    helping
    1.17
    Activations Density 0.015%

    No Known Activations