© 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. 152445
    Prev
    Next
    INDEX
    Explanations

    grams followed by specific words

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

    listing knowledge

    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
     allows
    0.52
     allowing
    0.51
     leveraging
    0.50
     permite
    0.49
    维护
    0.49
    </b>
    0.46
     messaging
    0.46
     Collections
    0.46
    ↵
    0.45
     allow
    0.45
    POSITIVE LOGITS
     isoniazid
    0.46
     விளக்க
    0.45
     kurs
    0.45
     lingered
    0.45
    Clk
    0.44
    ToPlot
    0.44
     inputted
    0.43
     greenish
    0.43
     vasomotor
    0.43
     professeurs
    0.42
    Activations Density 0.001%

    No Known Activations