© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 295
    Prev
    Next
    INDEX
    Explanations

    numbers in lists

    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
     Maks
    0.65
     Kn
    0.64
    ولي
    0.60
     Pro
    0.60
     ATLAS
    0.57
    ☜
    0.57
     সূরা
    0.57
    ynthetic
    0.56
    খের
    0.55
     Jol
    0.54
    POSITIVE LOGITS
    c
    1.10
    cc
    1.08
     c
    0.96
    ca
    0.95
    cd
    0.93
    ff
    0.90
    b
    0.88
    cb
    0.84
    f
    0.83
    ce
    0.83
    Activations Density 1.978%

    No Known Activations