© 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. 13653
    Prev
    Next
    INDEX
    Explanations

    formatting as bullet points

    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
    webserv
    1.78
    BSITE
    1.78
     ASA
    1.65
    carboxylic
    1.62
    𝕦
    1.62
    SdkVersion
    1.61
    CHCl
    1.61
     lương
    1.60
     Faro
    1.59
    ExpressCheckout
    1.58
    POSITIVE LOGITS
    ن
    1.29
    без
    1.25
    kom
    1.24
    pere
    1.24
    िनय
    1.24
     Retour
    1.22
    ст
    1.22
    瑰
    1.21
    ilius
    1.21
    ჟ
    1.20
    Activations Density 0.005%

    No Known Activations