© 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-IT
    5. 13-GEMMASCOPE-2-RES-16K
    7. 14818
    Prev
    Next
    INDEX
    Explanations

    sum of preceding numbers

    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_13_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
     just
    0.84
    <bos>
    0.78
    ster
    0.76
     EMS
    0.70
     गैस
    0.69
     even
    0.68
     long
    0.65
    ̃
    0.64
     низкой
    0.64
     Just
    0.63
    POSITIVE LOGITS
     영향을
    1.28
     위해
    1.25
     و
    1.22
     국가
    1.19
    ündet
    1.17
     때문에
    1.16
     anggota
    1.15
     akibat
    1.13
     पोशा
    1.12
     परिणामस्वरूप
    1.12
    Activations Density 0.001%

    No Known Activations