© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 25957
    Prev
    Next
    INDEX
    Explanations

    programming, math, science, or user requests

    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
    TP
    0.47
     blaze
    0.46
    _
    0.43
    IP
    0.42
    C
    0.42
    Open
    0.41
    K
    0.41
     uh
    0.41
    P
    0.40
    \
    0.40
    POSITIVE LOGITS
     स्वतंत्रता
    0.54
    തില്‍
    0.52
    étrique
    0.52
     spesso
    0.52
    리면
    0.52
     jezika
    0.51
    の前
    0.50
     często
    0.49
     വാക്ക
    0.49
     প্রতিষ্ঠিত
    0.48
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.