© 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. 13754
    Prev
    Next
    INDEX
    Explanations

    python code and data definitions

    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
     Said
    1.31
     ludzie
    1.28
    等等
    1.27
    שהו
    1.26
     etc
    1.23
     strane
    1.22
     pg
    1.21
     쪽
    1.20
     Fraternity
    1.20
     což
    1.20
    POSITIVE LOGITS
    esm
    1.62
    aş
    1.55
    alignment
    1.54
    oretically
    1.53
    esk
    1.50
    autumn
    1.49
     amputation
    1.49
    edale
    1.46
    lingwood
    1.46
    LOS
    1.46
    Activations Density 0.000%

    No Known Activations