© 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. 232598
    Prev
    Next
    INDEX
    Explanations

    submitted, I hope, read

    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
     nocturnal
    0.47
    пин
    0.42
    엘
    0.41
    代
    0.41
    يش
    0.40
     aquel
    0.39
     deterioro
    0.39
    ฟรี
    0.39
    ף
    0.38
    נת
    0.38
    POSITIVE LOGITS
     పద
    0.50
    amse
    0.49
     باید
    0.47
    ifrån
    0.47
    anging
    0.47
     andDevice
    0.47
    endem
    0.45
     цело
    0.45
    olog
    0.45
    alker
    0.44
    Activations Density 0.001%

    No Known Activations