© 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. 30723
    Prev
    Next
    INDEX
    Explanations

    question prompts

    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
     entanto
    -1.01
    šanai
    -0.99
    Prophet
    -0.96
    توضیحات
    -0.94
    ៏
    -0.93
    我说
    -0.92
     corriendo
    -0.92
     from
    -0.90
     hogy
    -0.90
    très
    -0.89
    POSITIVE LOGITS
     they
    2.02
     she
    2.00
     he
    1.75
     I
    1.63
     It
    1.49
     my
    1.48
     you
    1.44
     They
    1.43
     we
    1.40
     We
    1.30
    Activations Density 0.026%

    No Known Activations