© 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. 1406
    Prev
    Next
    INDEX
    Explanations

    both ... and .

    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
    th
    2.74
    comend
    2.67
    ς
    2.66
    st
    2.57
    ório
    2.44
     Analog
    2.43
    MemoryWarning
    2.40
    ्स
    2.40
    macros
    2.38
    ினார்
    2.37
    POSITIVE LOGITS
    nd
    3.22
     thirds
    2.90
     正規
    2.84
    rador
    2.72
    ﮈ
    2.59
    ﺑ
    2.55
    ное
    2.55
    рях
    2.53
    uparavant
    2.53
    瑁
    2.50
    Activations Density 0.426%

    No Known Activations