© 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. 7445
    Prev
    Next
    INDEX
    Explanations

    treating yourself like a friend

    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
    <bos>
    0.88
     eerst
    0.73
     everywhere
    0.71
     whenever
    0.69
    ことが多い
    0.67
     anywhere
    0.67
    SECONDARY
    0.65
     lots
    0.65
     Frequently
    0.64
     ontst
    0.64
    POSITIVE LOGITS
     만족
    0.78
    etlen
    0.77
    цей
    0.74
     덕
    0.73
     дово
    0.73
    kn
    0.72
     керів
    0.72
    ⵅ
    0.72
     해
    0.72
     공
    0.71
    Activations Density 0.014%

    No Known Activations