© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 13145
    Prev
    Next
    INDEX
    Explanations

    two or more

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_7_width_16k_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
    es
    3.07
    িমা
    2.64
    ი
    2.60
    esign
    2.52
    evu
    2.50
    تور
    2.50
    ej
    2.47
    evice
    2.45
    iwers
    2.38
    y
    2.32
    POSITIVE LOGITS
    াদ
    2.29
    ிய
    2.19
    venir
    2.18
     conoce
    2.14
    agement
    2.13
    न्नाथ
    2.12
    לים
    2.11
    тель
    2.07
    𝒶
    2.05
    lines
    2.04
    Activations Density 0.012%

    No Known Activations