© 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. 1561
    Prev
    Next
    INDEX
    Explanations

    conjunctions and lists

    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
    ，
    0.18
    )、
    0.18
     następnie
    0.17
     olefin
    0.17
     Kemudian
    0.17
     också
    0.17
     ৮
    0.17
    ）、
    0.16
    次に
    0.16
     containing
    0.16
    POSITIVE LOGITS
     and
    0.34
     etc
    0.34
     और
    0.33
     आणि
    0.32
    และ
    0.32
     và
    0.30
    और
    0.30
     અને
    0.29
     и
    0.29
     และ
    0.29
    Activations Density 2.641%

    No Known Activations