© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-262K
    7. 12315
    Prev
    Next
    INDEX
    Explanations

    restore your, acknowledge, backticks, commonsense

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_9_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    }{
    1.31
    ]]
    1.26
    ter
    1.18
     w
    1.13
     b
    1.11
    ou
    1.05
    ats
    1.04
     dob
    1.03
     πως
    1.01
    ))
    0.98
    POSITIVE LOGITS
    ی
    1.72
     тот
    1.70
     perangkat
    1.67
    <unused2109>
    1.66
    𝒚
    1.65
    يقة
    1.65
     doGet
    1.64
     methionine
    1.62
    𝕝
    1.62
    dür
    1.62
    Activations Density 0.000%

    No Known Activations