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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 60249
    Prev
    Next
    INDEX
    Explanations

    egg shells and nutshell

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

    anatomical terms and shell/egg-related terminology in scientific contexts.

    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_34/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
    Simon
    -0.75
    =\"
    -0.74
     Ownership
    -0.72
    Ye
    -0.71
    フェ
    -0.71
    ŭ
    -0.70
    digo
    -0.70
    ไทย
    -0.70
     Simon
    -0.68
     déchir
    -0.67
    POSITIVE LOGITS
     shell
    5.44
    shell
    4.72
     shells
    4.47
     Shell
    4.44
    Shell
    4.31
     SHELL
    3.56
    SHELL
    3.45
    shells
    3.22
     Shells
    3.22
     shelled
    2.73
    Activations Density 0.073%

    No Known Activations