© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 128346
    Prev
    Next
    INDEX
    Explanations

    shellfish, crabs, lobsters

    np_acts-logits-general · gemini-2.5-flash-lite

    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-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Stabilization
    0.45
    燧
    0.44
     thisComponent
    0.42
    suspended
    0.42
    오는
    0.42
     నిర్మాణ
    0.42
    writeFileSync
    0.40
    useEffect
    0.40
    আনুশকা
    0.40
     रेशियो
    0.40
    POSITIVE LOGITS
     crab
    0.85
     crabs
    0.85
     shrimps
    0.84
     prawn
    0.81
    🦞
    0.80
     shrimp
    0.80
    🦐
    0.79
     prawns
    0.78
     lobster
    0.74
    蟹
    0.74
    Activations Density 0.022%

    No Known Activations