© 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. 13193
    Prev
    Next
    INDEX
    Explanations

    two stages

    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
    また
    1.68
    ރ
    1.63
    からは
    1.62
    ちなみに
    1.59
    今回は
    1.59
    には
    1.58
    ތ
    1.57
    ukkan
    1.56
    についても
    1.53
     Daarnaast
    1.53
    POSITIVE LOGITS
     ngăn
    1.45
    margins
    1.43
    carboxylic
    1.34
    谋
    1.31
     margin
    1.30
     strerror
    1.28
     월
    1.26
     πολι
    1.24
     θεω
    1.22
     unstable
    1.19
    Activations Density 0.006%

    No Known Activations