© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 70017
    Prev
    Next
    INDEX
    Explanations

    marine gastropod shells and jade

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

    scientific terms related to mollusks and shells, particularly in taxonomic descriptions of sea snails and gastropods.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     soyez
    -1.30
    tieth
    -1.24
     terça
    -1.23
     fiches
    -1.19
    RequiresApi
    -1.19
    鷓
    -1.17
     GRATU
    -1.16
    のほうが
    -1.15
     beleid
    -1.13
     pensent
    -1.13
    POSITIVE LOGITS
     austere
    1.34
     때문에
    1.32
    Matéri
    1.30
     paleo
    1.30
    )
    1.27
     nuggets
    1.27
     storyteller
    1.27
     когда
    1.27
     delicacy
    1.26
     diminutive
    1.26
    Activations Density 0.038%

    No Known Activations