© 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. 31010
    Prev
    Next
    INDEX
    Explanations

    questions, decisions, or topics

    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
    them
    -1.50
    Them
    -1.08
    をします
    -1.05
     них
    -1.03
     它
    -1.02
     THEM
    -1.01
     レザー
    -1.01
     墙
    -1.01
    odora
    -1.00
     quello
    -0.98
    POSITIVE LOGITS
     that
    3.78
     we
    1.74
     they
    1.72
     που
    1.59
     mà
    1.42
     our
    1.34
     the
    1.32
     you
    1.31
     those
    1.20
     other
    1.14
    Activations Density 0.073%

    No Known Activations