© 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-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 9294
    Prev
    Next
    INDEX
    Explanations

    past trauma and its effects

    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
     子
    1.42
    똘
    1.26
     제주
    1.24
     科
    1.23
     을
    1.20
     ['
    1.19
     致
    1.19
    ֜
    1.18
     孔
    1.18
     فری
    1.18
    POSITIVE LOGITS
    Football
    1.24
    Mixed
    1.22
     vaak
    1.21
     peut
    1.16
    ळख
    1.15
     mercato
    1.08
    Merk
    1.08
    Often
    1.07
    Â
    1.07
     soms
    1.06
    Activations Density 0.002%

    No Known Activations