© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 163411
    Prev
    Next
    INDEX
    Explanations

    Cycling, BMX, Peloton

    np_acts-logits-general · gemini-2.5-flash-lite

    religious figures or physical activity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    łac
    0.48
    )=(\
    0.46
    িল
    0.44
    도
    0.44
    élo
    0.43
    仲間
    0.42
    TextColor
    0.42
     исче
    0.42
    éth
    0.42
    례
    0.41
    POSITIVE LOGITS
     Zeus
    0.54
     Chirop
    0.54
     Cycling
    0.50
     BMX
    0.50
     Semantic
    0.49
     Raven
    0.49
     behind
    0.48
     Chair
    0.48
     Peloton
    0.48
     cikin
    0.48
    Activations Density 0.000%

    No Known Activations