© 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. 67758
    Prev
    Next
    INDEX
    Explanations

    out/computer/apoptosis/perspectives/ingredients

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

    specialized terminology across different domains or professional jargon.

    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
     what
    -1.79
     or
    -1.66
     to
    -1.64
     -
    -1.56
     during
    -1.52
    3
    -1.42
     as
    -1.39
     the
    -1.34
    BeforeClass
    -1.31
     для
    -1.30
    POSITIVE LOGITS
     dokonce
    1.77
    łożyć
    1.59
     actrice
    1.59
     obiet
    1.55
    쾅
    1.52
     anfitrión
    1.51
     fût
    1.49
     этому
    1.48
     Entdecke
    1.48
     selera
    1.47
    Activations Density 0.086%

    No Known Activations