© 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. 51954
    Prev
    Next
    INDEX
    Explanations

    entrances and doors that

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

    distance from

    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
    жена
    0.45
    IES
    0.44
    l
    0.44
    gs
    0.43
    երի
    0.43
    puzzle
    0.42
    SOs
    0.42
    ၃
    0.42
    <ul>
    0.42
    arts
    0.41
    POSITIVE LOGITS
     seinem
    0.50
     რომელიც
    0.49
     如果
    0.48
     swoim
    0.48
     يجعل
    0.48
     swojego
    0.48
     به
    0.47
     audience
    0.47
     اپنے
    0.47
    宿
    0.47
    Activations Density 0.000%

    No Known Activations