© 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. 204479
    Prev
    Next
    INDEX
    Explanations

    magic never before

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

    historical events and specific entities

    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
     axiomatic
    0.53
    𝗘
    0.49
    Ко
    0.48
    ц
    0.47
    А
    0.47
    兗
    0.46
    не
    0.46
     в
    0.46
    М
    0.45
     повы
    0.45
    POSITIVE LOGITS
     Soybean
    0.47
     soybean
    0.45
    olata
    0.45
    olate
    0.43
     Mineral
    0.43
     কোম
    0.43
     catfish
    0.43
     Fisherman
    0.42
     Cycling
    0.42
    rigues
    0.42
    Activations Density 0.000%

    No Known Activations