© 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. 137841
    Prev
    Next
    INDEX
    Explanations

    learn, discuss, methods

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

    our sense of self

    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
    ্বস্ত
    0.46
    ಡ್ಡ
    0.46
     Plaintiff
    0.44
    𝒞
    0.44
     )}$
    0.43
     কাবুল
    0.43
     EXAMPLE
    0.42
     )}
    0.42
     aggrieved
    0.42
     Borrower
    0.42
    POSITIVE LOGITS
    йти
    0.48
    dell
    0.46
    トレ
    0.46
    讲解
    0.46
    discuss
    0.45
    IR
    0.45
    compatible
    0.45
    jno
    0.44
    veis
    0.44
    тин
    0.44
    Activations Density 0.000%

    No Known Activations