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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B
    5. 29-GEMMASCOPE-2-RES-16K
    7. 2709
    Prev
    Next
    INDEX
    Explanations

    sensitive with respect

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-pt/resid_post/layer_29_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
     HDTV
    1.00
    ऎ
    1.00
    
    0.96
    StringBuffer
    0.95
     muß
    0.90
    http
    0.90
     http
    0.89
    🖒
    0.86
     StringBuffer
    0.85
    군요
    0.85
    POSITIVE LOGITS
     queer
    1.85
     TikTok
    1.65
     Queer
    1.63
    TikTok
    1.62
    🫶
    1.60
     BIP
    1.51
    🥹
    1.48
     LGBTQ
    1.47
     ✨
    1.43
    🏳
    1.37
    Activations Density 0.709%

    No Known Activations