© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 90752
    Prev
    Next
    INDEX
    Explanations

    Explorer Edition, mathematicians, pearl, levels

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

    Many faced, underlying stepper, qualitative analysis

    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
    Negative Logits
     câble
    0.45
     मेजब
    0.45
    pre
    0.45
     सल
    0.44
    Submit
    0.44
     主
    0.43
    pu
    0.43
    mo
    0.42
     ควร
    0.42
    prechen
    0.42
    POSITIVE LOGITS
     alınd
    0.49
    더라구요
    0.48
    亮的
    0.45
     maxima
    0.44
     appoints
    0.44
     disturbances
    0.44
     emblems
    0.43
    μένες
    0.42
     mathematicians
    0.42
     supremum
    0.42
    Activations Density 0.000%

    No Known Activations