© 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. 20546
    Prev
    Next
    INDEX
    Explanations

    enjoying special moments

    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
     поверхности
    0.48
    ună
    0.48
     поверх
    0.47
    পদার্থ
    0.47
    Rash
    0.46
    """"
    0.46
    បី
    0.46
    ﺢ
    0.46
    Gel
    0.45
    Michel
    0.45
    POSITIVE LOGITS
     +
    0.52
     employee
    0.51
     fish
    0.51
    ed
    0.48
     angler
    0.47
     Sp
    0.47
    ie
    0.46
     lead
    0.46
     program
    0.45
     player
    0.45
    Activations Density 0.009%

    No Known Activations