© 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-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 1256
    Prev
    Next
    INDEX
    Explanations

    calendar, businesses, sentence, data structures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ↵
    0.51
    ergy
    0.47
     tofu
    0.46
     Rasp
    0.44
     centrally
    0.44
    er
    0.43
     Alpine
    0.43
     గురించి
    0.43
     Av
    0.43
     കേന്ദ്ര
    0.42
    POSITIVE LOGITS
    ри
    0.58
    к
    0.48
     گردد
    0.47
    кла
    0.46
    旛
    0.46
    мма
    0.45
    фи
    0.43
    iooni
    0.43
    SSON
    0.43
    מל
    0.42
    Activations Density 0.007%

    No Known Activations