© 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. 13-GEMMASCOPE-2-RES-65K
    7. 850
    Prev
    Next
    INDEX
    Explanations

    teacher model counterparts

    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_65k_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
    ﺅ
    0.59
     deniz
    0.58
     مشتمل
    0.56
    amet
    0.55
     జో
    0.55
     erity
    0.54
     jon
    0.54
    itol
    0.54
     জন্মগ্রহণ
    0.54
    ዓ
    0.53
    POSITIVE LOGITS
     counterparts
    0.99
     comparable
    0.81
     counterpart
    0.79
     அதே
    0.71
     decades
    0.66
     peers
    0.65
     Comparable
    0.65
     Basic
    0.65
    .
    0.65
    Comparable
    0.64
    Activations Density 1.635%

    No Known Activations