© 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. 17-GEMMASCOPE-2-RES-16K
    7. 4266
    Prev
    Next
    INDEX
    Explanations

    D followed by specific words

    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
    RootNamespace
    0.58
    cimentos
    0.58
    浒
    0.58
     সাপ্তাহ
    0.58
    ēng
    0.57
    椛
    0.57
    荨
    0.57
    ব্লিউ
    0.56
    lägt
    0.56
     ublox
    0.56
    POSITIVE LOGITS
    D
    1.93
     D
    1.87
    DS
    1.75
     DD
    1.72
     ড
    1.71
     డ
    1.71
    DP
    1.70
    DD
    1.68
    DM
    1.64
    DT
    1.63
    Activations Density 1.824%

    No Known Activations