© 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. 58062
    Prev
    Next
    INDEX
    Explanations

    invocation followed by numbers

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

    with a unusual occurrence

    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
    et
    0.54
     characterise
    0.52
     足
    0.51
    vgl
    0.49
     フラワー
    0.49
     至
    0.48
    wijl
    0.48
     声
    0.47
    etal
    0.47
     手
    0.47
    POSITIVE LOGITS
    किस्तान
    0.47
     Unusual
    0.44
     sabah
    0.43
     Mechanic
    0.43
     Synthetic
    0.42
     Substit
    0.41
     Consolidated
    0.39
    Substitution
    0.39
     Certified
    0.39
    โจ
    0.38
    Activations Density 0.000%

    No Known Activations