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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 1784
    Prev
    Next
    INDEX
    Explanations

    walking and moving

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

    actions following "then" or "I"

    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_53_width_65k_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
     accruing
    0.42
     desarrollando
    0.41
    鰥
    0.40
     beneficia
    0.40
     dijadikan
    0.40
     coinciding
    0.40
    꾀
    0.39
    잦
    0.39
     बढ़ावा
    0.38
     implementar
    0.38
    POSITIVE LOGITS
     walked
    1.42
    walk
    1.26
     walks
    1.23
     walk
    1.23
     walking
    1.16
     WALK
    1.15
     strolled
    1.14
    Walk
    1.13
     Walk
    1.09
     stood
    1.09
    Activations Density 0.445%

    No Known Activations