© 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. 48356
    Prev
    Next
    INDEX
    Explanations

    essay writings

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

    text art symbols

    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
    م
    0.98
    न
    0.83
    ン
    0.82
    在
    0.78
    در
    0.77
    க்
    0.75
    ك
    0.72
    로
    0.71
    มอง
    0.70
    ల
    0.69
    POSITIVE LOGITS
    3
    0.91
    1
    0.87
    5
    0.84
    la
    0.78
    are
    0.77
    ла
    0.76
    arb
    0.75
    2
    0.74
    та
    0.73
    arit
    0.73
    Activations Density 0.006%

    No Known Activations