© 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. 2337
    Prev
    Next
    INDEX
    Explanations

    Unto

    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
     🌱
    0.93
     गांव
    0.91
    <unused367>
    0.91
    <unused342>
    0.90
    <unused189>
    0.89
    <unused733>
    0.88
    <unused725>
    0.88
    <unused521>
    0.87
    <unused1032>
    0.87
    <unused2017>
    0.86
    POSITIVE LOGITS
    n
    0.95
    iquement
    0.92
    ながら
    0.86
    im
    0.86
    हीं
    0.86
    anwhile
    0.85
     vezes
    0.84
    ne
    0.84
    O
    0.82
     anderem
    0.81
    Activations Density 0.395%

    No Known Activations