© 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. 173147
    Prev
    Next
    INDEX
    Explanations

    suffixes like ment, ance, cy, ator

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

    pipeline general multiplierachter

    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
     a
    1.00
     to
    0.98
     Sánchez
    0.76
     the
    0.75
     at
    0.73
     is
    0.72
    0
    0.71
    “
    0.71
     of
    0.68
    a
    0.66
    POSITIVE LOGITS
     दुसरे
    0.82
    ла
    0.82
    ле
    0.75
    ни
    0.70
     সম্পূর্ন
    0.70
    맇
    0.70
     সাধারন
    0.69
    त
    0.69
    াইয়৷
    0.68
    ת
    0.68
    Activations Density 0.565%

    No Known Activations