© 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. 209689
    Prev
    Next
    INDEX
    Explanations

    teaching fellow

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

    Page numbers and code placeholders

    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
     Stain
    0.50
     G
    0.49
     Coastal
    0.48
     Basket
    0.48
     Mays
    0.48
     Feather
    0.47
     Influence
    0.47
     Into
    0.47
     Interstate
    0.47
     Railroad
    0.47
    POSITIVE LOGITS
    🦷
    0.54
     matematica
    0.53
     homeopathy
    0.53
     rectum
    0.51
     metastases
    0.50
     teorema
    0.49
     numai
    0.49
     metastasis
    0.49
    ЕНИЕ
    0.48
    ‌ای
    0.48
    Activations Density 0.001%

    No Known Activations