© 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. 9-GEMMASCOPE-2-RES-16K
    7. 437
    Prev
    Next
    INDEX
    Explanations

    sexually explicit content

    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_9_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
    anah
    1.19
    erte
    1.19
    ০
    1.16
    る
    1.13
    েজ
    1.12
     monomials
    1.11
    دأ
    1.10
    ो
    1.08
    iato
    1.07
    辦法
    1.07
    POSITIVE LOGITS
    ウス
    1.25
    imageView
    1.20
    𝐞
    1.18
    Friend
    1.10
    媧
    1.07
    婿
    1.06
    nt
    1.06
    xpath
    1.06
    می
    1.05
    folk
    1.04
    Activations Density 0.504%

    No Known Activations