© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 3071
    Prev
    Next
    INDEX
    Explanations

    traditional Korean

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

    product descriptions and features

    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
     совокуп
    0.41
    Responding
    0.38
     tartış
    0.38
    戕
    0.36
    瞋
    0.36
     belirl
    0.35
    妨
    0.35
    罹
    0.35
    质疑
    0.34
     Tayyip
    0.34
    POSITIVE LOGITS
     hotel
    0.58
     hotels
    0.55
     villas
    0.55
     hôtel
    0.54
     hoteles
    0.52
     Hotel
    0.52
     cottages
    0.52
     food
    0.50
    Hotel
    0.50
     bungalows
    0.50
    Activations Density 0.929%

    No Known Activations