© 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. 12217
    Prev
    Next
    INDEX
    Explanations

    C++ programming

    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
    醐
    2.62
    žne
    2.49
     "/"
    2.40
    ары
    2.40
    พาะ
    2.35
    kiewicz
    2.30
    の人気
    2.30
     skal
    2.29
    ᵑ
    2.26
    cısı
    2.25
    POSITIVE LOGITS
    ⁣
    3.07
    ⁢
    2.87
    𝗁
    2.61
    head
    2.59
     ‌
    2.55
    Ь
    2.54
    வீன
    2.53
    efi
    2.51
    weight
    2.48
     Bytes
    2.46
    Activations Density 0.009%

    No Known Activations