© 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. 67860
    Prev
    Next
    INDEX
    Explanations

    birthday cake, domestic child, New Years, Tennessee, about the, hardy fuchsia, Molokai, edition console, Survival hack

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

    another option

    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
     are
    0.40
     were
    0.40
     diversas
    0.39
     aberta
    0.38
    q
    0.38
     definida
    0.38
    leer
    0.37
    lerinin
    0.37
    lin
    0.37
     páginas
    0.37
    POSITIVE LOGITS
    อีก
    0.45
     আবারও
    0.43
    另一种
    0.41
    もう
    0.40
    说法
    0.40
     আরেক
    0.40
    頷
    0.39
     annoyance
    0.39
    另一
    0.38
    ALERT
    0.38
    Activations Density 0.027%

    No Known Activations