© 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. 218789
    Prev
    Next
    INDEX
    Explanations

    sequences of descriptors and specifics

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

    describing states or processes

    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
    情况下
    0.47
    ្រី
    0.45
    ruits
    0.45
    悩
    0.44
    よい
    0.44
     chaos
    0.44
    ieran
    0.43
    பெரும்
    0.43
    腥
    0.43
     Lieutenant
    0.43
    POSITIVE LOGITS
    🆈
    0.47
     പറഞ്ഞ
    0.47
    젹
    0.46
     applic
    0.45
    iliy
    0.45
     dùng
    0.45
    TRO
    0.44
    á
    0.44
     domać
    0.44
    ciamo
    0.43
    Activations Density 0.001%

    No Known Activations