© 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. 123618
    Prev
    Next
    INDEX
    Explanations

    awards granted

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

    languages and numbers in lists

    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
    רו
    0.52
    Digite
    0.52
     את
    0.50
    छ
    0.49
    𝚛
    0.48
    做事
    0.48
    ג
    0.48
    ט
    0.47
    Evet
    0.46
    Objet
    0.46
    POSITIVE LOGITS
     tại
    0.54
     concurrently
    0.51
     intermittently
    0.48
     επίσης
    0.44
     ongoing
    0.44
     facilitated
    0.43
     networked
    0.43
     enabled
    0.43
     concomit
    0.42
     facilitation
    0.42
    Activations Density 0.000%

    No Known Activations