© 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. 128541
    Prev
    Next
    INDEX
    Explanations

    while anticipating

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

    "to"ignore"

    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
     infallible
    0.51
    ⌯
    0.49
    exhaustive
    0.48
     あなた
    0.48
     enmity
    0.48
     ง่าย
    0.47
     অভিনন্দন
    0.47
     एवरीवन
    0.46
     betrayal
    0.46
     страш
    0.46
    POSITIVE LOGITS
     re
    0.49
    张
    0.45
    in
    0.44
     reclaimed
    0.44
     steered
    0.43
     salvaged
    0.42
     in
    0.42
    %;
    0.40
     occasionally
    0.40
     if
    0.40
    Activations Density 0.000%

    No Known Activations