© 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. 16-GEMMASCOPE-2-RES-262K
    7. 144254
    Prev
    Next
    INDEX
    Explanations

    Empire State Building

    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_16_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
    t
    1.13
    y
    1.03
    ف
    0.94
    h
    0.90
    IN
    0.89
    0.88
    In
    0.85
    ए
    0.84
    AT
    0.82
    The
    0.81
    POSITIVE LOGITS
    رويج
    0.71
     of
    0.69
     الصين
    0.62
    ﻲ
    0.60
     المركز
    0.59
     الكرة
    0.59
    чиго
    0.59
    rizzle
    0.59
     klassischen
    0.59
     ايش
    0.58
    Activations Density 0.000%

    No Known Activations