© 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. 72677
    Prev
    Next
    INDEX
    Explanations

    fish and fish embryos

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

    scientific names and classifications of fish species.

    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
    ULTURAL
    -1.46
     monstrous
    -1.39
     discrepan
    -1.39
    の方も
    -1.38
    TOON
    -1.35
     apetito
    -1.29
     télécharger
    -1.28
    紇
    -1.25
    ISSION
    -1.25
     Recreational
    -1.23
    POSITIVE LOGITS
     when
    1.53
     with
    1.42
     to
    1.37
     When
    1.36
     fishes
    1.33
    ője
    1.31
     Keuangan
    1.30
     only
    1.29
    Pisces
    1.28
     upacara
    1.27
    Activations Density 0.090%

    No Known Activations