© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 128346
    Prev
    Next
    INDEX
    Explanations

    crab, lobster, shrimp, Scrapy

    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
    useEffect
    0.44
    燧
    0.42
     Stabilization
    0.41
     रेशियो
    0.41
     నిర్మాణ
    0.41
    धीन
    0.41
    ومین
    0.39
    ักษณะ
    0.39
    ardless
    0.38
    भोपाल
    0.38
    POSITIVE LOGITS
     crab
    0.77
     crabs
    0.77
     shrimp
    0.73
     shrimps
    0.71
    🦐
    0.68
     prawns
    0.67
     Crab
    0.66
     crustaceans
    0.66
    蟹
    0.66
     lobster
    0.64
    Activations Density 0.027%

    No Known Activations