© 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. 39889
    Prev
    Next
    INDEX
    Explanations

    identifying sources of

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

    origin or provision

    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
    ун
    0.89
    0.82
     stylized
    0.79
    ید
    0.77
    اري
    0.77
     выполнение
    0.75
    িনবার্গ
    0.73
    もら
    0.70
    е
    0.70
    о
    0.68
    POSITIVE LOGITS
     sources
    1.44
     Sources
    1.42
     Source
    1.21
    Sources
    1.21
     SOURCES
    1.17
     źród
    1.17
    sources
    1.16
     SOURCE
    1.15
     fonti
    1.14
     source
    1.13
    Activations Density 0.033%

    No Known Activations