© 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
    2. Gemma-3-4B-IT
    3. 17-GEMMASCOPE-2-RES-16K
    4. 1703
    Prev
    Next
    INDEX
    Explanations

    python program script

    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
     possibilità
    1.11
    ங்களின்
    1.02
     mogelijk
    1.00
     можливо
    1.00
    呔
    0.99
     possibilidade
    0.97
     bisa
    0.96
    ться
    0.95
    жает
    0.94
    BOSS
    0.93
    POSITIVE LOGITS
    ische
    1.36
    nf
    1.31
    దేశ
    1.30
    
    1.29
    на
    1.28
    
    1.27
    
    1.26
    icill
    1.25
    women
    1.24
    walking
    1.22
    Activations Density 0.463%

    No Known Activations