© 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. 3467
    Prev
    Next
    INDEX
    Explanations

    relative comparison

    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
    いる
    1.17
    ون
    1.12
    いた
    1.09
    ors
    1.05
     आठ
    1.01
    وان
    0.99
    א
    0.96
    ים
    0.92
    вое
    0.91
     उपलब्धि
    0.91
    POSITIVE LOGITS
    to
    1.15
    '
    0.98
     Relative
    0.89
    ต์
    0.87
    p
    0.86
    is
    0.84
     relativ
    0.84
     jim
    0.80
     to
    0.80
    orak
    0.79
    Activations Density 0.093%

    No Known Activations