© 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. 250546
    Prev
    Next
    INDEX
    Explanations

    cities grow, resulting terrain; active states

    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
     idling
    0.48
    AR
    0.46
     predictable
    0.45
    R
    0.43
    TE
    0.43
    \%
    0.42
    <
    0.42
    $\
    0.41
    *
    0.41
     limiting
    0.41
    POSITIVE LOGITS
     ಭ
    0.56
     نبی
    0.53
     غور
    0.53
     لی
    0.52
     قام
    0.52
     ਇੱਕ
    0.51
     інте
    0.51
     भा
    0.51
     був
    0.51
     championed
    0.51
    Activations Density 0.000%

    No Known Activations