© 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. 237269
    Prev
    Next
    INDEX
    Explanations

    offer to invoicing

    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
     संख्या
    0.46
    র্ড
    0.45
     沒有
    0.44
     meninas
    0.44
    d
    0.43
    u
    0.42
    ikli
    0.42
    rones
    0.42
     arreg
    0.42
     všetky
    0.42
    POSITIVE LOGITS
    另一个
    0.48
    我们
    0.48
    자와
    0.45
    者的
    0.44
    人们
    0.43
    华
    0.43
    .•
    0.42
     oğlu
    0.42
     подоб
    0.42
    客户
    0.41
    Activations Density 0.001%

    No Known Activations