© 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. 38874
    Prev
    Next
    INDEX
    Explanations

    technical and medical terms

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

    parenthetical notations of proper names and identifiers.

    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
     ſeveral
    -0.93
     geholfen
    -0.91
    sians
    -0.90
    AME
    -0.88
    MongoClient
    -0.88
    becoming
    -0.85
    ऍ
    -0.84
     油
    -0.84
    nance
    -0.83
    ళ
    -0.83
    POSITIVE LOGITS
     from
    1.18
    )
    0.92
     also
    0.92
    アプリケーション
    0.91
    粼
    0.91
     liburan
    0.87
     memasuki
    0.87
     mewujudkan
    0.86
    ),
    0.86
    SALUD
    0.86
    Activations Density 0.095%

    No Known Activations