© 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. 17-GEMMASCOPE-2-RES-16K
    7. 3835
    Prev
    Next
    INDEX
    Explanations

    code logging output

    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_17_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
     Give
    0.88
    Give
    0.82
     Giving
    0.82
     )
    0.76
     Certainly
    0.76
     giving
    0.76
     Allowing
    0.76
    ](/
    0.75
    ↵↵
    0.75
     granting
    0.75
    POSITIVE LOGITS
    셈
    0.77
     Jumlah
    0.76
     perempuan
    0.73
    াড়াও
    0.72
    नियां
    0.71
    Number
    0.70
    this
    0.69
     숫자
    0.69
     sayı
    0.69
    ចំនួន
    0.68
    Activations Density 0.030%

    No Known Activations