© 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. 60864
    Prev
    Next
    INDEX
    Explanations

    access, provide, leadership

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

    listings with bolded titles

    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
    ließlich
    0.50
    unächst
    0.46
    arcía
    0.42
    ósfera
    0.42
    asper
    0.41
     ክፍል
    0.40
    𒊬
    0.40
    alist
    0.40
    <unused1854>
    0.40
    䅐
    0.39
    POSITIVE LOGITS
    :
    0.48
    энер
    0.46
     merkle
    0.42
     (!)
    0.42
    0.40
     NOAA
    0.39
     ADMINISTR
    0.39
     ${
    0.39
     UCLA
    0.39
    <td>
    0.39
    Activations Density 0.044%

    No Known Activations