© 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. 83570
    Prev
    Next
    INDEX
    Explanations

    after the fact

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

    professional closings

    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
    数の
    0.55
    地の
    0.53
    数が
    0.52
    IDES
    0.45
    гән
    0.45
     disturbs
    0.45
    ў
    0.45
    マックス
    0.44
    வலி
    0.44
     เสียง
    0.44
    POSITIVE LOGITS
    Picked
    0.48
    ture
    0.45
     Leiter
    0.44
    Prepared
    0.44
     ihm
    0.44
     ihn
    0.43
     Janssen
    0.43
     ഏറ്റ
    0.43
     ？
    0.43
     Meille
    0.43
    Activations Density 0.001%

    No Known Activations