© 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. 142238
    Prev
    Next
    INDEX
    Explanations

    needed phase measurements reports metabolic search understand

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

    analyzing, searching, or representing lists

    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
     ר
    0.57
     r
    0.49
     diverging
    0.47
     جه
    0.46
    intersects
    0.46
     څر
    0.46
     これらの
    0.46
    的处理
    0.46
     dobrze
    0.45
     verrou
    0.45
    POSITIVE LOGITS
    ᑭ
    0.50
    amet
    0.48
    तं
    0.47
    S
    0.47
    वं
    0.46
    दिशा
    0.46
    炘
    0.45
     Furniture
    0.44
    ulman
    0.44
    მ
    0.43
    Activations Density 0.001%

    No Known Activations