© 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. 189669
    Prev
    Next
    INDEX
    Explanations

    extra blade

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

    assuming a context

    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
    d
    0.57
    l
    0.56
    sun
    0.49
    h
    0.49
    n
    0.47
    lun
    0.46
    las
    0.46
    land
    0.46
    line
    0.45
    da
    0.45
    POSITIVE LOGITS
     interessante
    0.54
     interessant
    0.52
     améliorer
    0.50
     orientale
    0.49
    劒
    0.48
    欴
    0.47
     intéressante
    0.46
     الداخل
    0.46
     remplacement
    0.45
     essentielle
    0.45
    Activations Density 0.000%

    No Known Activations