© 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. 63712
    Prev
    Next
    INDEX
    Explanations

    sequences of digits

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

    conditional restrictions or possibilities

    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
    更是
    0.42
     ka
    0.41
     caregiver
    0.41
    anjan
    0.40
     RISK
    0.39
     fornisce
    0.39
     TO
    0.39
     OF
    0.39
    ⇝
    0.38
    lems
    0.38
    POSITIVE LOGITS
    Deine
    0.48
    ByteArray
    0.46
    hôtel
    0.46
    Authorize
    0.46
    一时
    0.45
     హైదరాబాద్
    0.45
    会議
    0.44
    䙷
    0.44
    を利用
    0.44
     său
    0.43
    Activations Density 0.000%

    No Known Activations