© 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. 73863
    Prev
    Next
    INDEX
    Explanations

    phrases after certain words

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

    Policy Gradients, Tremor, Bearer

    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
     c
    0.52
     agrees
    0.49
     rents
    0.49
     soothe
    0.49
     chalet
    0.47
     circa
    0.47
    يج
    0.47
     reunite
    0.47
     gateways
    0.46
    c
    0.46
    POSITIVE LOGITS
    𝒉
    0.54
    σιμο
    0.52
    𝑭
    0.50
    ufthansa
    0.49
     Від
    0.48
     UVA
    0.47
    ქვთ
    0.47
     تبدی
    0.46
    phenylsulfanyl
    0.45
     購入
    0.45
    Activations Density 0.000%

    No Known Activations