© 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. 122072
    Prev
    Next
    INDEX
    Explanations

    related errors, healthy, plans, relevant personality, untreated

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

    contextual conjunctions

    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
    legi
    0.46
     सेंस
    0.46
     hér
    0.45
     เขา
    0.45
    ateri
    0.44
    kül
    0.44
     [...]
    0.44
     terd
    0.43
     GÉN
    0.43
    apeake
    0.43
    POSITIVE LOGITS
    יות
    0.55
    ص
    0.52
    겸
    0.48
    נות
    0.47
    سط
    0.46
    מצע
    0.46
     complemented
    0.46
    executed
    0.45
    ᱗
    0.45
    とした
    0.45
    Activations Density 0.002%

    No Known Activations