© 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. 7-GEMMASCOPE-2-RES-16K
    7. 12683
    Prev
    Next
    INDEX
    Explanations

    varying levels of

    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
    ழுகு
    1.85
     기타
    1.69
     나머
    1.64
     民
    1.57
     등으로
    1.57
     원
    1.53
    ரத்தில்
    1.53
    )$}
    1.53
     그다음에
    1.51
     層
    1.49
    POSITIVE LOGITS
    Pok
    1.80
    точка
    1.62
    Emmanuel
    1.46
    Packed
    1.42
    Cert
    1.38
     tapis
    1.35
    Sophie
    1.34
    รวม
    1.34
     Certificates
    1.34
     zmi
    1.33
    Activations Density 0.004%

    No Known Activations