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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 7925
    Prev
    Next
    INDEX
    Explanations

    promoting violence scenarios

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_13_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
    லோச
    1.42
     foes
    1.41
     suppuration
    1.38
    rosyn
    1.37
    솟
    1.35
    rocyte
    1.33
    ylob
    1.33
    \{-\
    1.33
    <bbox>
    1.32
    ousal
    1.32
    POSITIVE LOGITS
     basically
    1.64
     guys
    1.63
     Honestly
    1.61
     freaking
    1.61
     देखील
    1.60
    Honestly
    1.54
     Basically
    1.51
     ​​
    1.48
     kalian
    1.44
    非常的
    1.44
    Activations Density 0.089%

    No Known Activations