© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-16K
    7. 1107
    Prev
    Next
    INDEX
    Explanations

    numerical tokens followed by punctuation

    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_12_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
    on
    0.96
    ears
    0.91
    ਂ
    0.88
    az
    0.87
    ંગ
    0.86
    od
    0.84
    एशन
    0.82
    os
    0.80
    onian
    0.80
    ed
    0.78
    POSITIVE LOGITS
     endast
    1.01
    컴
    0.97
     eten
    0.96
    nach
    0.94
     ფორ
    0.94
     apporter
    0.91
     simonsen
    0.91
     έχει
    0.90
     noten
    0.89
    larını
    0.88
    Activations Density 0.001%

    No Known Activations