© 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. 232616
    Prev
    Next
    INDEX
    Explanations

    anticipates feedback clients searches

    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
    Not in Any Lists

    No Comments

    Negative Logits
     américains
    0.51
     offent
    0.49
    αν
    0.48
     Sval
    0.48
    මු
    0.48
    рів
    0.48
     chunks
    0.47
    욌
    0.46
    стар
    0.46
     rekonstru
    0.46
    POSITIVE LOGITS
     серд
    0.45
    意志
    0.45
    渺
    0.43
    ociety
    0.42
    anation
    0.42
    cis
    0.42
    瘴
    0.41
     চীনের
    0.41
    parte
    0.41
     आएगी
    0.41
    Activations Density 0.001%

    No Known Activations