© 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. 136488
    Prev
    Next
    INDEX
    Explanations

    apart, mentor, where, Aron, strings

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

    While violet is more, sky is blue

    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
    ٹ
    0.61
    մ
    0.55
    łow
    0.51
     haszn
    0.49
     খাজ
    0.48
    urk
    0.48
     käytt
    0.47
    पाट
    0.46
    țion
    0.46
    ⓔ
    0.46
    POSITIVE LOGITS
     sentient
    0.46
     первый
    0.43
    .]:
    0.43
    முதல்
    0.38
     darkly
    0.38
     longitudinally
    0.37
     practitioners
    0.37
     usur
    0.37
     electing
    0.37
     reserve
    0.37
    Activations Density 0.000%

    No Known Activations