© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 119988
    Prev
    Next
    INDEX
    Explanations

    taxes payable

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

    structured lists and data

    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
    DET
    0.47
    朿
    0.46
    carboxylic
    0.46
    𝗼
    0.46
    کا
    0.45
    कालिक
    0.45
    ᓴ
    0.45
     उत्पा
    0.45
    អ្នក
    0.45
     ಆದ್ದರಿಂದ
    0.45
    POSITIVE LOGITS
     ISBN
    0.52
    <0x0D>
    0.51
     '=',
    0.49
     verifies
    0.45
    n
    0.45
     vít
    0.44
    0.44
    🥱
    0.43
     systém
    0.43
    ヂ
    0.43
    Activations Density 0.001%

    No Known Activations