© 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-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 13041
    Prev
    Next
    INDEX
    Explanations

    climbing or grappling activities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_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
     Loretta
    0.56
    eradish
    0.55
    វេ
    0.54
    碟
    0.54
     Spitze
    0.52
    सैन
    0.51
     Timatic
    0.50
    倌
    0.50
     شفاف
    0.49
    Encoding
    0.49
    POSITIVE LOGITS
     climbing
    1.81
     climbers
    1.76
     Climbing
    1.75
     climber
    1.74
     climb
    1.52
     climbed
    1.50
     climbs
    1.48
    攀
    1.38
    🧗
    1.38
     Climb
    1.33
    Activations Density 0.288%

    No Known Activations