© 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. 17425
    Prev
    Next
    INDEX
    Explanations

    followed by

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

    what follows

    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
    だったら
    0.45
     فإن
    0.40
    みると
    0.37
     enfim
    0.37
     thì
    0.37
    नातील
    0.36
    则
    0.36
     보면
    0.36
     entrev
    0.36
     فانه
    0.36
    POSITIVE LOGITS
     followed
    3.94
    followed
    3.77
     seguido
    3.38
     diikuti
    3.23
     seguida
    3.20
     suivie
    2.88
     suivi
    2.72
     gevol
    2.53
     seguito
    2.38
     suiv
    2.31
    Activations Density 0.188%

    No Known Activations