© 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. 13212
    Prev
    Next
    INDEX
    Explanations

    lie on your back

    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
     people
    1.32
    ‪
    1.31
    <strong>
    1.31
    K
    1.30
    En
    1.29
     also
    1.28
     is
    1.26
    In
    1.22
    keen
    1.21
    ens
    1.20
    POSITIVE LOGITS
     opcoes
    2.42
     cuestiones
    2.42
    亍
    2.39
     கட்டடக்கலை
    2.34
     அதிசயங்கள்
    2.30
     stvar
    2.28
    Aslamualaikum
    2.27
     questões
    2.26
     adaptador
    2.24
     funcionalidades
    2.24
    Activations Density 0.001%

    No Known Activations