© 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. 139976
    Prev
    Next
    INDEX
    Explanations

    listing items or ingredients

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

    `package` or `searching` or `Produce`

    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
     সম্পর্কিত
    0.47
     concomit
    0.45
    Pag
    0.44
    க்கான
    0.44
    IActionResult
    0.43
    Pand
    0.43
     Pand
    0.42
     دیتی
    0.42
    湾
    0.42
    contained
    0.42
    POSITIVE LOGITS
     পর্
    0.49
     पर्दे
    0.47
    meny
    0.46
     רו
    0.46
    cks
    0.44
    vedo
    0.42
     禁止
    0.42
    ʺ
    0.42
     ceny
    0.41
     너무
    0.41
    Activations Density 0.002%

    No Known Activations