© 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. 2755
    Prev
    Next
    INDEX
    Explanations

    Abbreviations and acronyms

    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
     മൂ
    0.51
     கீழ்
    0.45
    ándor
    0.42
     జ
    0.42
    েও
    0.40
     دارد
    0.39
    谗
    0.39
     చెబు
    0.38
     tehát
    0.38
    ᚕ
    0.38
    POSITIVE LOGITS
    N
    0.69
    c
    0.68
    os
    0.68
    x
    0.66
    un
    0.66
    ad
    0.63
    v
    0.62
    リ
    0.62
    re
    0.61
    2
    0.59
    Activations Density 0.285%

    No Known Activations