© 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-IT
    5. 13-GEMMASCOPE-2-RES-16K
    7. 2293
    Prev
    Next
    INDEX
    Explanations

    hero sections and imperialism

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_13_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    
    1.54
    竴
    1.37
     comp
    1.35
     toon
    1.34
     деньги
    1.34
    উপর
    1.31
    卋
    1.31
     money
    1.30
    ейчас
    1.30
    Tidak
    1.30
    POSITIVE LOGITS
    ious
    1.14
    త్మ
    1.14
    ductory
    1.14
    faction
    1.14
    legraph
    1.13
    кої
    1.08
    кой
    1.07
     dit
    1.06
    滤
    1.04
    hemy
    1.04
    Activations Density 0.001%

    No Known Activations