Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-16K
    4. 12444
    Prev
    Next
    INDEX
    Explanations

    async await and clojure forms

    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_16k_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
     active
    0.40
    Lazy
    0.38
     unrecognized
    0.38
    ਕਰ
    0.37
     passive
    0.37
     활
    0.37
     actif
    0.37
     facilitators
    0.37
     निष्क्रिय
    0.37
     견
    0.36
    POSITIVE LOGITS
     vendita
    0.44
     $-\
    0.44
     Qxb
    0.43
     ($\
    0.43
     beweg
    0.43
    ()-
    0.42
     -.
    0.41
     Bankr
    0.41
    स्‍या
    0.41
     பால்
    0.40
    Activations Density 0.036%

    No Known Activations