© 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. 116707
    Prev
    Next
    INDEX
    Explanations

    crystal longer

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

    healthy relationships and anatomy

    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
    ث
    0.49
    سي
    0.48
    சார
    0.47
    ع
    0.47
    satz
    0.47
    플레이
    0.46
    م
    0.46
     instabilities
    0.46
    ය
    0.46
     cré
    0.46
    POSITIVE LOGITS
     आगा
    0.47
    㑓
    0.44
     scorecard
    0.43
     रोकने
    0.42
    itemBackground
    0.42
    aca
    0.42
    badge
    0.42
    ama
    0.41
     humiliated
    0.41
    えます
    0.41
    Activations Density 0.001%

    No Known Activations