© 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. 185505
    Prev
    Next
    INDEX
    Explanations

    phrases indicating action or state

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

    multilingual classification

    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
    ickt
    0.51
    ኣ
    0.49
    소서
    0.49
    ighty
    0.48
    또한
    0.48
    +$
    0.47
    akte
    0.47
    xn
    0.47
    emotional
    0.46
    4
    0.45
    POSITIVE LOGITS
     தின
    0.49
     vermiş
    0.49
     polygonal
    0.46
     শিব
    0.46
     petrochemical
    0.45
     lavage
    0.45
     penulis
    0.44
     سٹ
    0.44
    dzie
    0.43
     निगम
    0.43
    Activations Density 0.000%

    No Known Activations