© 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-3-12B-IT
    5. 24-GEMMASCOPE-2-RES-16K
    7. 2521
    Prev
    Next
    INDEX
    Explanations

    words ending sentences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_24_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
     Puedes
    0.46
     چهار
    0.46
     Aucun
    0.46
     ArrayRef
    0.45
     जिसमे
    0.45
     हालांकि
    0.44
     Ethnicity
    0.44
     色
    0.44
     BatchNorm
    0.44
     Độ
    0.42
    POSITIVE LOGITS
     zouden
    0.63
     hadden
    0.61
     zullen
    0.55
     eivät
    0.55
     werden
    0.54
     waren
    0.54
     to
    0.53
     furent
    0.53
     seraient
    0.52
     saranno
    0.52
    Activations Density 0.001%

    No Known Activations