© 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. 4086
    Prev
    Next
    INDEX
    Explanations

    rock climbing

    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
     Koffer
    -0.71
     groundwater
    -0.70
    stw
    -0.69
    куп
    -0.69
     Groundwater
    -0.68
    świad
    -0.66
    AQ
    -0.66
    lsen
    -0.65
     drawdown
    -0.65
    шма
    -0.64
    POSITIVE LOGITS
     mountaine
    3.08
     climbing
    2.80
     climbers
    2.61
     climber
    2.50
     Mountaine
    2.41
     Climbing
    2.23
     climb
    2.23
     climbed
    2.19
    Climbing
    2.19
     mountain
    2.11
    Activations Density 0.046%

    No Known Activations