© 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. 224481
    Prev
    Next
    INDEX
    Explanations

    money, real estate, and miscellaneous detail

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

    visa on arrival

    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
    시간
    0.54
    ୃ
    0.52
     भिखारी
    0.51
    વિ
    0.47
    業界
    0.47
    પ્ર
    0.47
    τικών
    0.46
    發表
    0.46
    东方
    0.46
    वर्ण
    0.46
    POSITIVE LOGITS
     pare
    0.47
     kip
    0.46
     ə
    0.45
     rõ
    0.44
     terr
    0.43
     Szym
    0.41
     kyl
    0.41
     bato
    0.41
     karl
    0.41
     Lloyd
    0.41
    Activations Density 0.001%

    No Known Activations