© 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-IT
    5. 22-GEMMASCOPE-2-RES-16K
    7. 1579
    Prev
    Next
    INDEX
    Explanations

    code and math operators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_22_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Aye
    0.91
    HX
    0.88
     $\{$
    0.85
     MF
    0.84
     HX
    0.83
     XT
    0.83
     ATG
    0.83
     JL
    0.81
     Bro
    0.81
    ᴬ
    0.80
    POSITIVE LOGITS
     m
    1.83
     d
    1.83
     b
    1.82
     h
    1.76
     p
    1.73
     g
    1.72
     c
    1.68
     r
    1.66
     w
    1.58
     k
    1.58
    Activations Density 1.311%

    No Known Activations