© 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. 205178
    Prev
    Next
    INDEX
    Explanations

    completing sections

    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
    ot
    0.52
     athlete
    0.51
    ilingual
    0.46
    atype
    0.45
    first
    0.43
    or
    0.43
    с
    0.43
     attractor
    0.42
     employee
    0.41
     athletes
    0.41
    POSITIVE LOGITS
     תו
    0.53
     βα
    0.50
     FURTHER
    0.48
     방법을
    0.48
     צי
    0.47
     되
    0.47
     %+
    0.47
     urma
    0.46
     회
    0.45
     微
    0.45
    Activations Density 0.007%

    No Known Activations