© 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. 62223
    Prev
    Next
    INDEX
    Explanations

    essay titles and concepts

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

    argues complex issues, weighing pros and cons

    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
     (
    0.56
     ((
    0.52
     ('
    0.51
     (§
    0.50
     (-\
    0.49
     "("
    0.49
     আবার
    0.48
     '[
    0.48
     ("
    0.48
     '|
    0.48
    POSITIVE LOGITS
     최고의
    0.50
     intolerable
    0.46
     sebepler
    0.46
     deserve
    0.45
     outperform
    0.44
     beher
    0.44
     adversity
    0.44
     kinerja
    0.43
     különböző
    0.43
     catalyze
    0.43
    Activations Density 0.004%

    No Known Activations