© 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. 6098
    Prev
    Next
    INDEX
    Explanations

    past trauma and difficult experiences

    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
     freelance
    0.87
     ügy
    0.86
    中の
    0.86
    http
    0.85
    @
    0.84
    logs
    0.83
    签约
    0.83
     স্থগিত
    0.82
    のを
    0.82
    中で
    0.82
    POSITIVE LOGITS
    faceted
    1.34
     童
    1.28
    sibling
    1.23
     বিদ্যাল
    1.19
     باپ
    1.19
    缺失
    1.17
     siblings
    1.17
     बचपन
    1.17
    rianças
    1.16
     定义
    1.16
    Activations Density 0.204%

    No Known Activations