© 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. 185445
    Prev
    Next
    INDEX
    Explanations

    simultaneously re-acquire, level, NOK

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

    0 and 1

    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
    ITTING
    0.51
    дә
    0.50
     തന്നെയാണ്
    0.49
    szön
    0.46
    ܂
    0.44
     זי
    0.44
    కున్న
    0.43
     बरकरार
    0.43
    剻
    0.43
    ოტ
    0.42
    POSITIVE LOGITS
     celulares
    0.43
     tabl
    0.41
    Frm
    0.40
    cm
    0.39
    ocyt
    0.39
    人群
    0.39
    sugar
    0.39
    理
    0.39
    sero
    0.38
     Robles
    0.38
    Activations Density 0.001%

    No Known Activations