© 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-16K
    7. 12571
    Prev
    Next
    INDEX
    Explanations

    piercings and cartilage

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

    questions, asks, player, plant

    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_16k_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
     Sachsen
    0.55
     dữ
    0.54
    g
    0.53
    ari
    0.52
     Ba
    0.51
     Yu
    0.50
     Gä
    0.50
     Dmitri
    0.49
     Thé
    0.48
     fondly
    0.48
    POSITIVE LOGITS
     snake
    0.47
    इसका
    0.46
    ਊ
    0.43
    Agricultural
    0.42
     belly
    0.42
     refrigeration
    0.42
     tubular
    0.42
    অর্থাৎ
    0.41
     hydraulic
    0.41
    ਿਆ
    0.41
    Activations Density 0.010%

    No Known Activations