© 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. 10-GEMMASCOPE-RES-131K
    7. 11845
    Prev
    Next
    INDEX
    Explanations

    killer whales, brown fox, ravenous animals

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

    names of animal 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
    簓
    -1.61
     میز
    -1.56
     ISSUE
    -1.50
    嫑
    -1.49
     ſever
    -1.48
     legendar
    -1.47
    LError
    -1.45
    tovat
    -1.45
     vœux
    -1.45
    TION
    -1.43
    POSITIVE LOGITS
     just
    1.94
    er
    1.69
     has
    1.67
     any
    1.67
     where
    1.45
     and
    1.41
     on
    1.40
     some
    1.39
     he
    1.38
    x
    1.34
    Activations Density 0.022%

    No Known Activations