© 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
    2. Gemma-3-1B
    3. 7-GEMMASCOPE-2-RES-16K
    4. 13595
    Prev
    Next
    INDEX
    Explanations

    json format

    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
    𝔹
    1.64
    دع
    1.50
    breakable
    1.46
    쭈
    1.43
    stacks
    1.42
    莢
    1.41
     Caz
    1.40
    níku
    1.40
    潺
    1.39
     Greene
    1.38
    POSITIVE LOGITS
     terrestrial
    1.37
     buena
    1.34
    Normal
    1.31
     geen
    1.28
     tengah
    1.28
     merda
    1.25
     keine
    1.22
     buona
    1.22
     maupun
    1.21
     monog
    1.20
    Activations Density 0.462%

    No Known Activations