© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 260649
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    parquet
    0.53
    𝕟
    0.52
     QUE
    0.51
     NKG
    0.51
    뛴
    0.51
    텟
    0.51
    Technische
    0.50
    ئن
    0.49
    腃
    0.48
    𒂗
    0.47
    POSITIVE LOGITS
    mless
    0.45
     Early
    0.43
     Chapter
    0.43
    bli
    0.42
     Preface
    0.42
     temprano
    0.41
     Demons
    0.41
     brave
    0.40
     Jerome
    0.40
    وامی
    0.39
    Activations Density 0.000%

    No Known Activations