© 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. 128691
    Prev
    Next
    INDEX
    Explanations

    genus names and species

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

    Wikipedia-style section headers for dates or names of places, species, or historical entities.

    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
    </b>
    -1.77
     even
    -1.70
     which
    -1.68
     Even
    -1.63
     or
    -1.62
     by
    -1.56
     In
    -1.56
     with
    -1.55
     for
    -1.48
    ":
    -1.43
    POSITIVE LOGITS
     باسلام
    1.67
    を選択します
    1.46
     reiterated
    1.41
    にします
    1.40
     rosario
    1.40
     insiste
    1.37
     disting
    1.36
    扨
    1.34
     开始
    1.34
     indepen
    1.30
    Activations Density 0.184%

    No Known Activations