© 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. 5319
    Prev
    Next
    INDEX
    Explanations

    T-shirt, tutorial, towers, trained, trench

    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
    er
    0.90
    ޓ
    0.81
    ंदा
    0.80
    getRepository
    0.78
     tuner
    0.77
    erler
    0.77
    TeX
    0.77
     decorated
    0.76
    前进
    0.76
    ுள்ளார்
    0.75
    POSITIVE LOGITS
    rival
    0.75
    恤
    0.74
    ropic
    0.71
    प्ता
    0.71
    rium
    0.71
    र्फ
    0.70
     messages
    0.70
    empo
    0.69
     сумма
    0.68
     пера
    0.68
    Activations Density 0.244%

    No Known Activations