© 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-3-270M
    5. 15-GEMMASCOPE-2-RES-16K
    7. 5301
    Prev
    Next
    INDEX
    Explanations

    was a constant companion

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-pt/resid_post/layer_15_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
     Черка
    1.82
    瑋
    1.77
     Looks
    1.71
    Looks
    1.70
    발
    1.68
     Sees
    1.65
    opub
    1.60
    thumbs
    1.59
    rainian
    1.58
     تشوف
    1.58
    POSITIVE LOGITS
     Geschichte
    0.85
     番
    0.83
    forever
    0.80
    ificates
    0.80
     พระเจ้า
    0.77
    arrayOf
    0.75
     Indira
    0.74
    IFICATE
    0.74
     relinquish
    0.73
     reintroduced
    0.72
    Activations Density 0.043%

    No Known Activations