© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 39646
    Prev
    Next
    INDEX
    Explanations

    freshwater and saltwater environments

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

    words related to water environments, particularly "freshwater" and other water body terms.

    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
    ↵↵
    -3.13
    犼
    -2.73
    馓
    -2.63
     famoso
    -2.48
     nin
    -2.41
     crappy
    -2.22
    快要
    -2.20
     "
    -2.20
     verschieden
    -2.17
     praktisch
    -2.14
    POSITIVE LOGITS
    when
    2.97
    ဴ
    2.83
    This
    2.81
     こ
    2.67
    which
    2.66
    There
    2.64
    Since
    2.47
     Contrary
    2.42
    عف
    2.41
    Unlike
    2.39
    Activations Density 0.006%

    No Known Activations