© 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. 169050
    Prev
    Next
    INDEX
    Explanations

    occupying elements

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

    control and increasingly

    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
    T
    0.55
    firefox
    0.47
    ρές
    0.42
    sière
    0.41
    8
    0.41
    V
    0.41
     Ziegler
    0.41
    ReactDOM
    0.41
    тэй
    0.40
    Y
    0.40
    POSITIVE LOGITS
     intensify
    0.53
     توقع
    0.51
    uch
    0.51
     سعيد
    0.50
     செய
    0.48
    ilas
    0.47
    áno
    0.46
    十一章
    0.46
     obiettivo
    0.46
    ig
    0.45
    Activations Density 0.000%

    No Known Activations