© 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. 82684
    Prev
    Next
    INDEX
    Explanations

    programming languages

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

    nn.Linear

    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
    Negative Logits
    और
    0.34
    🇮
    0.33
     स्वातंत्र्य
    0.33
    ót
    0.32
     damned
    0.32
     अन्
    0.32
     Syrian
    0.31
     BUT
    0.31
    AND
    0.30
    었고
    0.30
    POSITIVE LOGITS
    یثیت
    0.34
     hout
    0.32
    ၏
    0.32
     réaliser
    0.31
    찬가지
    0.31
    ўным
    0.31
    াচিত
    0.31
     apiKey
    0.31
    ്യാപ
    0.31
    یتے
    0.30
    Activations Density 0.358%

    No Known Activations