© 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. 249117
    Prev
    Next
    INDEX
    Explanations

    fashion, finance, and Thailand

    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
    Recipes
    0.51
    }=
    0.47
     isto
    0.47
    THERE
    0.47
     ಕಡಿಮೆ
    0.46
     Isto
    0.45
     ছাড়াও
    0.45
    ករ
    0.45
    istemas
    0.45
    調理
    0.44
    POSITIVE LOGITS
     he
    0.51
     j
    0.49
     exclamation
    0.47
     signaling
    0.47
     gauge
    0.46
     dimensional
    0.45
     hangar
    0.45
     chalet
    0.44
     সাংবাদিকদের
    0.44
     va
    0.44
    Activations Density 0.001%

    No Known Activations