© 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
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 10850
    Prev
    Next
    INDEX
    Explanations

    Kubernetes `apps/v1` Deployments

    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
    မျှ
    2.79
    াদ্র
    2.73
    ⓤ
    2.68
    iennent
    2.66
    ⵄ
    2.61
    ⁱ
    2.61
    ⓗ
    2.60
    ⺝
    2.60
    matchCondition
    2.58
    ⬯
    2.58
    POSITIVE LOGITS
    sty
    2.44
    م
    2.44
    t
    2.31
    lant
    2.24
    pore
    2.24
    ر
    2.22
     ad
    2.13
    matic
    2.07
    r
    2.06
    l
    2.06
    Activations Density 0.019%

    No Known Activations