© 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
    2. Gemma-3-270M
    3. 12-GEMMASCOPE-2-RES-16K
    4. 6884
    Prev
    Next
    INDEX
    Explanations

    is a descriptor

    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_12_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
    ずつ
    0.80
     example
    0.76
     precedent
    0.70
     and
    0.68
    ).}
    0.60
     already
    0.59
     themselves
    0.57
    勉
    0.54
    example
    0.54
     potential
    0.51
    POSITIVE LOGITS
     bietet
    2.69
     delves
    2.64
     깊
    2.61
     зву
    2.60
    推出
    2.60
    是一款
    2.59
     velvety
    2.55
    është
    2.54
     Анг
    2.53
     مرحبا
    2.51
    Activations Density 0.289%

    No Known Activations