© 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. 1701
    Prev
    Next
    INDEX
    Explanations

    phrases of state and achievement

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

    at play, in mind, in distress, in favor, on special, on display

    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
     enemigos
    0.29
     весьма
    0.27
     undertakings
    0.26
     emociones
    0.26
     रूपों
    0.26
    痈
    0.25
     sanciones
    0.25
     anderes
    0.25
     období
    0.25
     mesmas
    0.24
    POSITIVE LOGITS
     contention
    0.31
     prace
    0.30
     effect
    0.30
     prominence
    0.29
     immediate
    0.28
     ‎
    0.28
     proie
    0.27
     sre
    0.27
     detail
    0.26
     contest
    0.26
    Activations Density 0.649%

    No Known Activations