© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 201658
    Prev
    Next
    INDEX
    Explanations

    plot points and story elements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     امروز
    0.50
     dimensiones
    0.48
     EBIT
    0.48
     Aujourd
    0.46
     hundert
    0.46
     किमान
    0.46
     ನಾವು
    0.45
    <unused2173>
    0.44
    heim
    0.43
     Austria
    0.43
    POSITIVE LOGITS
     row
    0.53
     prayer
    0.45
     Wrang
    0.44
     savings
    0.43
     medication
    0.43
     crash
    0.43
     conspiracy
    0.41
    ствия
    0.41
    LECTION
    0.41
    िसू
    0.41
    Activations Density 0.007%

    No Known Activations