© 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. 109288
    Prev
    Next
    INDEX
    Explanations

    moving around

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

    movement around freely

    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
     arrivé
    0.44
     Directly
    0.44
     చేరు
    0.43
     dearest
    0.42
    𝖊
    0.42
    স্থা
    0.42
     Ecke
    0.42
    糗
    0.42
     पहुंचकर
    0.41
     எதிர்க்க
    0.41
    POSITIVE LOGITS
     freely
    0.76
     roaming
    0.68
     navigating
    0.66
     wandering
    0.65
     wanders
    0.62
     свободно
    0.61
     wander
    0.60
     घूम
    0.60
    遍历
    0.60
     wandered
    0.59
    Activations Density 0.211%

    No Known Activations