© 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. 12943
    Prev
    Next
    INDEX
    Explanations

    passion about

    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
    ✙
    2.83
    𝕝
    2.81
    ulmonary
    2.79
    麿
    2.74
    ℍ
    2.72
    𝕟
    2.69
    なわち
    2.68
    朧
    2.67
    𝕣
    2.64
     dériv
    2.64
    POSITIVE LOGITS
    t
    2.58
    d
    2.49
    s
    2.33
    nast
    2.26
    c
    2.25
    dick
    2.25
    sas
    2.15
    tay
    2.13
    rados
    2.03
    才是
    2.03
    Activations Density 0.018%

    No Known Activations