© 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. 34-GEMMASCOPE-RES-131K
    7. 64041
    Prev
    Next
    INDEX
    Explanations

    who someone is or is becoming

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    ᄉ
    -0.88
     MATTERS
    -0.81
     znajd
    -0.78
     résistant
    -0.77
    \\\\
    -0.77
    Bạn
    -0.77
     mando
    -0.74
     PLAC
    -0.74
    viation
    -0.73
     получает
    -0.73
    POSITIVE LOGITS
     aspire
    1.45
     Becoming
    1.19
     becoming
    1.18
     geworden
    1.13
    Become
    1.09
     asp
    1.09
     Become
    1.07
    Becoming
    1.05
     became
    1.04
     strives
    1.03
    Activations Density 0.023%

    No Known Activations