© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 55930
    Prev
    Next
    INDEX
    Explanations

    railroad lines and tracks

    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
     Straßen
    -0.89
    Elevator
    -0.75
     Elev
    -0.74
    turma
    -0.71
     buggy
    -0.70
    jogador
    -0.69
    BEAT
    -0.69
    McGraw
    -0.68
     ľah
    -0.68
    empor
    -0.66
    POSITIVE LOGITS
     tracks
    2.00
     track
    1.57
    tracks
    1.45
    Tracks
    1.18
    track
    1.17
     Tracks
    1.16
     TRACK
    1.14
     lines
    1.00
    TRACK
    0.99
    Track
    0.96
    Activations Density 0.045%

    No Known Activations