© 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. 6175
    Prev
    Next
    INDEX
    Explanations

    teaching and promoting education

    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
    ul
    0.37
    :
    0.37
    name
    0.36
    xb
    0.36
    all
    0.35
    <sup>
    0.35
    sear
    0.35
    ла
    0.35
    এর
    0.35
    ул
    0.34
    POSITIVE LOGITS
     التعليم
    0.44
     thérapeut
    0.44
     kerja
    0.41
     मान्यता
    0.39
    㳒
    0.39
     Educação
    0.38
     saluran
    0.38
     Förderung
    0.38
     virtuelle
    0.38
     স্বীকৃতি
    0.37
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.