© 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. 248414
    Prev
    Next
    INDEX
    Explanations

    describes objects and actions

    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
    ন
    0.54
    كر
    0.48
    plemente
    0.48
    नियों
    0.46
     ushered
    0.46
    قال
    0.46
    ခ
    0.44
    arnish
    0.43
    ক
    0.43
     occured
    0.43
    POSITIVE LOGITS
    idikan
    0.48
     murky
    0.46
     Cubic
    0.46
     myriad
    0.45
     cubic
    0.45
    শোধ
    0.45
     hoeveel
    0.44
     silky
    0.43
    cubic
    0.43
     uner
    0.42
    Activations Density 0.001%

    No Known Activations