© 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. 86778
    Prev
    Next
    INDEX
    Explanations

    want them to in tweets for this

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

    specific contextual terms

    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
    ，
    0.54
    ،
    0.54
     با
    0.54
     keyed
    0.50
     interpreters
    0.50
    、
    0.50
     with
    0.49
     چک
    0.48
    <0xC2>
    0.48
     soles
    0.47
    POSITIVE LOGITS
     তিনটা
    0.48
    向け
    0.44
    ulfide
    0.44
     ইরান
    0.44
     Initializes
    0.43
    祜
    0.43
    úrese
    0.43
    ilberger
    0.43
     ආකාර
    0.43
     হয়েছিল
    0.42
    Activations Density 0.002%

    No Known Activations