© 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. 13123
    Prev
    Next
    INDEX
    Explanations

    any [qualifier]

    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
     It
    0.75
     in
    0.73
    所有的
    0.68
    ssä
    0.67
     L
    0.66
     Islanders
    0.64
     wichtigen
    0.64
     Some
    0.63
    in
    0.62
    sı
    0.61
    POSITIVE LOGITS
    ,
    0.90
    ור
    0.80
     qualsiasi
    0.75
    ,/
    0.74
     любую
    0.73
    any
    0.72
     qualunque
    0.70
    вропей
    0.70
    2
    0.70
    ף
    0.69
    Activations Density 0.081%

    No Known Activations