© 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. 17-GEMMASCOPE-2-RES-16K
    7. 738
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     individuelle
    0.61
     individuale
    0.61
    Denn
    0.57
    <>();
    0.56
    收费
    0.55
    ज्
    0.54
     indywidual
    0.53
     individuais
    0.53
    個
    0.52
    த்திரம்
    0.52
    POSITIVE LOGITS
     similar
    3.23
    similar
    2.86
    Similar
    2.85
     Similar
    2.77
     similares
    2.67
     similaire
    2.60
     similarity
    2.55
     semelhante
    2.54
     comparable
    2.51
     similaires
    2.51
    Activations Density 5.875%

    No Known Activations