© 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. 94912
    Prev
    Next
    INDEX
    Explanations

    when once followed by a consequence

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

    stars and constellations in different hemispheres

    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
     Writing
    0.50
    牒
    0.49
    BLINK
    0.48
    .
    0.45
     layouts
    0.43
    _
    0.41
     handwriting
    0.41
     bylaws
    0.40
     dec
    0.40
     escritura
    0.40
    POSITIVE LOGITS
    ਸ਼ਨ
    0.52
     систему
    0.52
     மண்ண
    0.51
     चर्चा
    0.50
     bilgi
    0.50
    pper
    0.49
    娼
    0.48
     प्रणाली
    0.48
     championed
    0.47
     актуа
    0.46
    Activations Density 0.001%

    No Known Activations