© 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-3-4B-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 800
    Prev
    Next
    INDEX
    Explanations

    keywords followed by modifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_17_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
     personajes
    1.19
     从
    1.15
     monologue
    1.11
     ordinance
    1.08
     शुक्रिया
    1.05
     desej
    1.03
     magnifying
    1.00
    仲間
    1.00
     censorship
    1.00
     certamente
    0.99
    POSITIVE LOGITS
    en
    1.22
    தை
    1.17
    nk
    1.15
    utives
    1.15
    d
    1.15
    yad
    1.14
    liel
    1.13
    suff
    1.13
    𝒂
    1.12
    юць
    1.11
    Activations Density 0.000%

    No Known Activations