© 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. 7009
    Prev
    Next
    INDEX
    Explanations

    linear algebra matrices operations

    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
    ı
    0.47
    0
    0.47
    set
    0.45
     me
    0.44
    ઇ
    0.44
     kem
    0.43
    yle
    0.43
    by
    0.43
    Kem
    0.43
    inda
    0.42
    POSITIVE LOGITS
     coprodu
    0.54
     Казино
    0.48
    ᱓
    0.48
    ᱖
    0.45
     centrales
    0.45
    ᱕
    0.45
     კარ
    0.45
     inexplic
    0.44
    ᠴ
    0.44
     libras
    0.44
    Activations Density 0.013%

    No Known Activations