© 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. 33875
    Prev
    Next
    INDEX
    Explanations

    Taylor Swift, chairs, Ford

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

    questions and answers or CEO requests

    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
    λ
    0.50
     ZH
    0.49
     sợi
    0.48
     Chao
    0.48
     renal
    0.47
     derivadas
    0.46
     irritable
    0.46
    𝕥
    0.46
     amni
    0.46
    9
    0.45
    POSITIVE LOGITS
    ObjectUnderTest
    0.47
    obus
    0.46
     вули
    0.46
     الحكومة
    0.45
    وابة
    0.45
    baru
    0.44
     Governmental
    0.44
    ORIA
    0.44
     Governo
    0.44
    ੱਕ
    0.44
    Activations Density 0.000%

    No Known Activations