© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 14294
    Prev
    Next
    INDEX
    Explanations

    suffering and ransom

    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
    <eos>
    0.96
    .</
    0.94
    '.'
    0.92
     zcela
    0.89
     באופן
    0.89
     nooit
    0.88
     stets
    0.88
    ">(
    0.87
     (".
    0.87
    kap
    0.87
    POSITIVE LOGITS
    所以
    2.00
     所以
    1.94
    所以我
    1.91
    なので
    1.90
    所以在
    1.89
     nên
    1.72
    ですので
    1.63
    Therefore
    1.62
    だったので
    1.61
     Therefore
    1.55
    Activations Density 0.425%

    No Known Activations