© 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. 22-GEMMASCOPE-2-RES-16K
    7. 7679
    Prev
    Next
    INDEX
    Explanations

    checking types and conditions

    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_22_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
     interconnected
    1.20
    謨
    1.11
     configured
    1.11
     sandwiched
    1.10
    FBSDKGraph
    1.10
     ascending
    1.09
     converges
    1.05
     俺
    1.05
     메시
    1.05
    Fetched
    1.05
    POSITIVE LOGITS
    d
    1.71
    b
    1.59
    e
    1.57
    a
    1.52
    t
    1.51
    c
    1.49
    n
    1.42
    j
    1.40
    f
    1.35
    m
    1.32
    Activations Density 0.009%

    No Known Activations