© 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. 184194
    Prev
    Next
    INDEX
    Explanations

    seem dubious

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

    explaining reasoning or definitions

    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
     перевоз
    0.52
    挑戦
    0.50
     الوط
    0.45
    ทำ
    0.45
     إعادة
    0.45
    moires
    0.44
    蒔
    0.44
     अप्र
    0.44
     अधिकारियों
    0.44
     నిర్ణ
    0.44
    POSITIVE LOGITS
     discourse
    0.52
     delas
    0.48
    un
    0.47
     generic
    0.47
     verbal
    0.46
     monitored
    0.46
     nii
    0.45
     Running
    0.44
     the
    0.44
    e
    0.44
    Activations Density 0.000%

    No Known Activations