© 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. 88634
    Prev
    Next
    INDEX
    Explanations

    increased quantity or comparison

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

    more

    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
    1.18
    ۔
    0.98
    ।
    0.94
     are
    0.90
    at
    0.88
    were
    0.88
     Conversely
    0.79
    ’
    0.77
     imped
    0.74
     inkl
    0.74
    POSITIVE LOGITS
    на
    1.09
    ん
    0.90
    (
    0.89
     niż
    0.85
    ную
    0.82
    ية
    0.82
     than
    0.81
    いた
    0.81
    ли
    0.79
    ล
    0.79
    Activations Density 0.300%

    No Known Activations