© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 134310
    Prev
    Next
    INDEX
    Explanations

    holiday, Christmas, New, Map

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

    recent data, test, steel, alone

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     \
    0.58
    ’
    0.55
     Δ
    0.51
     is
    0.50
     έ
    0.47
     α
    0.46
     l
    0.45
     ဝ
    0.45
     ㅁ
    0.45
    after
    0.44
    POSITIVE LOGITS
    Nelson
    0.52
    graf
    0.50
    <footer>
    0.50
    .??.??"]
    0.48
    ्यूड
    0.47
     प्रशांत
    0.46
    elihood
    0.46
    plotlib
    0.46
    因此
    0.45
     उनके
    0.45
    Activations Density 0.000%

    No Known Activations