© 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. 172318
    Prev
    Next
    INDEX
    Explanations

    vary, granted, policy, lived, every, ISO

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

    understanding needs and desires

    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
     encapsulate
    0.54
    ्ज
    0.51
    Ń
    0.49
     encapsulates
    0.49
     attend
    0.47
     accentuate
    0.47
     admirers
    0.46
     besieged
    0.46
    </em>
    0.46
     evoc
    0.46
    POSITIVE LOGITS
     Commandments
    0.46
    лями
    0.46
    設定
    0.45
     indivíduos
    0.45
     Bank
    0.44
    (
    0.44
     Borrower
    0.44
     Второй
    0.43
    KS
    0.43
    什麼
    0.43
    Activations Density 0.001%

    No Known Activations