© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 11850
    Prev
    Next
    INDEX
    Explanations

    election, elections

    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
    ing
    2.90
    ی
    2.89
    anediyl
    2.48
    ிக்க
    2.37
    ي
    2.30
    కు
    2.29
    ്
    2.25
    ت
    2.23
    ioen
    2.22
    iteration
    2.18
    POSITIVE LOGITS
    icleta
    2.33
    ths
    2.32
    ো
    2.31
     unión
    2.29
    бто
    2.27
    屜
    2.26
    Cours
    2.25
    Proguard
    2.21
    ल्याण
    2.21
    зма
    2.18
    Activations Density 0.001%

    No Known Activations