© 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. 53078
    Prev
    Next
    INDEX
    Explanations

    `haw`, `sow`, `awning`

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

    awk commands

    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
     a
    1.20
    is
    0.88
     i
    0.87
    al
    0.79
     u
    0.78
     y
    0.77
    ли
    0.76
    ia
    0.76
    го
    0.69
     V
    0.68
    POSITIVE LOGITS
    вной
    0.80
    ческого
    0.79
     فی
    0.78
    زی
    0.78
    その
    0.74
    𝙰
    0.74
    quele
    0.74
    کی
    0.70
    стів
    0.70
    ciamo
    0.69
    Activations Density 0.282%

    No Known Activations