© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 48609
    Prev
    Next
    INDEX
    Explanations

    who is involved

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    hasht
    0.42
     fortunate
    0.39
    qos
    0.39
     potvr
    0.38
    婇
    0.38
     sights
    0.38
    info
    0.37
    তো
    0.37
     leaders
    0.36
    مش
    0.36
    POSITIVE LOGITS
    әп
    0.50
    ieval
    0.49
    澥
    0.47
    त्रे
    0.46
     современного
    0.46
     Ио
    0.44
    冼
    0.43
     тер
    0.43
     nobis
    0.42
    Ъ
    0.42
    Activations Density 0.004%

    No Known Activations