© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 12664
    Prev
    Next
    INDEX
    Explanations

    numbers and dates

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

    numbers in texts

    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_16k_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
    '
    0.73
     as
    0.70
     be
    0.63
    2
    0.63
    $
    0.61
    ü
    0.60
     aswell
    0.55
    .$
    0.55
     blom
    0.55
    רי
    0.52
    POSITIVE LOGITS
    𝒈
    0.56
    нг
    0.56
    𝚙
    0.54
    zov
    0.53
     १८
    0.52
     १७
    0.52
    ку
    0.52
     deviates
    0.51
    نين
    0.50
    southern
    0.50
    Activations Density 0.399%

    No Known Activations