© 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. 237462
    Prev
    Next
    INDEX
    Explanations

    by car

    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
     vasocon
    0.58
     elas
    0.56
     misery
    0.54
     vasodil
    0.49
     shutdowns
    0.48
     delas
    0.48
     e
    0.47
     exem
    0.47
     bre
    0.47
     sees
    0.47
    POSITIVE LOGITS
    人们
    0.51
    人們
    0.51
    𝐍
    0.47
    মন্দ
    0.46
    alakip
    0.46
    𝗞
    0.46
    ্সে
    0.45
    চিতের
    0.44
    Additionally
    0.43
     ಆದರೆ
    0.43
    Activations Density 0.001%

    No Known Activations