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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 13942
    Prev
    Next
    INDEX
    Explanations

    as your

    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_7_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
    ტი
    3.40
    lerim
    2.95
    MediaStore
    2.77
    пло
    2.74
    стана
    2.73
    chyma
    2.71
    terna
    2.70
    刳
    2.69
    uities
    2.64
    טית
    2.57
    POSITIVE LOGITS
    ர்ந்த
    2.89
    marginLeft
    2.82
    రి
    2.76
     activiteiten
    2.69
     பலர்
    2.43
    сть
    2.42
    りに
    2.41
    申し上げ
    2.33
     phosphorylated
    2.33
     comple
    2.32
    Activations Density 0.017%

    No Known Activations