© 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. 68186
    Prev
    Next
    INDEX
    Explanations

    particular housing, County from, we serve

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

    explanations and definitions

    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
    囷
    0.51
    வருக
    0.47
    處
    0.47
    莆
    0.47
    ﮩ
    0.46
     gehe
    0.45
    కు
    0.45
    处的
    0.44
    沿着
    0.44
    枣
    0.44
    POSITIVE LOGITS
    Skill
    0.49
    Vs
    0.48
    time
    0.46
    Avengers
    0.45
    pet
    0.45
     ประเภท
    0.44
     ultimatum
    0.44
    Cs
    0.44
    On
    0.43
    Fact
    0.43
    Activations Density 0.000%

    No Known Activations