© 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-262K
    7. 38958
    Prev
    Next
    INDEX
    Explanations

    organize, categorize, present information

    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_262k_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
     нее
    0.46
     बल्कि
    0.45
    ၏
    0.42
     it
    0.40
     कारण
    0.40
     she
    0.38
    oxifen
    0.37
     Victoria
    0.36
    ophilia
    0.36
    conom
    0.36
    POSITIVE LOGITS
     ორ
    0.50
     organize
    0.48
     różne
    0.46
     categorize
    0.46
    這樣子
    0.44
    Estos
    0.43
     نشوف
    0.42
    옛
    0.42
    Tem
    0.41
    Lists
    0.41
    Activations Density 0.000%

    No Known Activations