© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 75476
    Prev
    Next
    INDEX
    Explanations

    question words often

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ﮑ
    0.48
    ശേഷ
    0.46
    пикир
    0.45
    URNIZOR
    0.45
    optimize
    0.44
    რებული
    0.44
    Ꮥ
    0.44
     AppBsky
    0.44
     clickView
    0.43
    кли
    0.42
    POSITIVE LOGITS
     almost
    0.53
     often
    0.52
     usually
    0.52
     they
    0.51
     areas
    0.51
    0.49
     area
    0.48
     keeps
    0.46
     They
    0.46
     kept
    0.46
    Activations Density 0.015%

    No Known Activations