© 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. 78123
    Prev
    Next
    INDEX
    Explanations

    rejecting

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

    addressing issues and worst-case scenarios

    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
     worldRank
    0.44
    ˖
    0.44
    Ƙ
    0.42
    乩
    0.42
    するとき
    0.41
    лизи
    0.41
     postępow
    0.41
    Ꮨ
    0.41
    ন্ধ
    0.41
     een
    0.40
    POSITIVE LOGITS
     EVP
    0.52
    மாய
    0.46
     thuyết
    0.45
     остались
    0.43
     rahu
    0.40
    ים
    0.40
    F
    0.40
    ژه
    0.39
    E
    0.39
     understatement
    0.39
    Activations Density 0.000%

    No Known Activations