© 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-262K
    7. 15052
    Prev
    Next
    INDEX
    Explanations

    hundreds of

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

    hundreds thousands millions

    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
     and
    0.72
     و
    0.64
     väga
    0.63
     e
    0.62
     at
    0.60
     an
    0.59
     及
    0.59
     anemia
    0.58
     estrogen
    0.57
     was
    0.57
    POSITIVE LOGITS
    Hundreds
    0.89
    Thousands
    0.86
     десятки
    0.83
     decenas
    0.83
     Hundreds
    0.80
     centena
    0.80
     тысяч
    0.79
    \
    0.77
     hundreds
    0.77
     thousands
    0.76
    Activations Density 0.018%

    No Known Activations