© 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. 22-GEMMASCOPE-RES-131K
    7. 34710
    Prev
    Next
    INDEX
    Explanations

    predatory animals

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

    words related to predatory animals like lions, wolves, and other wild carnivores.

    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_22/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
     OBIT
    -1.44
     amour
    -1.37
    山形
    -1.35
     MEMO
    -1.34
     Khart
    -1.33
    omalies
    -1.32
     TECHNIQUE
    -1.32
    tismo
    -1.31
    定価
    -1.28
    富山
    -1.28
    POSITIVE LOGITS
    .
    1.66
     instincts
    1.63
     he
    1.60
    8
    1.50
    6
    1.42
    9
    1.35
     ferocious
    1.35
     slumber
    1.30
    Ecotoxicity
    1.27
    -
    1.24
    Activations Density 0.039%

    No Known Activations