© 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. 12-GEMMASCOPE-2-RES-262K
    7. 30467
    Prev
    Next
    INDEX
    Explanations

    pill / pills

    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_262k_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
    cido
    1.88
     việc
    1.66
     Sanit
    1.66
    ca
    1.62
    ּ
    1.60
    pytorch
    1.59
    phosphat
    1.59
    anse
    1.57
    ../../../
    1.55
     Solicitors
    1.55
    POSITIVE LOGITS
    できる
    2.41
    ो
    2.38
    きた
    2.28
    しまう
    2.02
    ના
    1.99
    ή
    1.97
    اه
    1.95
    larda
    1.95
    िट
    1.93
     reste
    1.93
    Activations Density 0.002%

    No Known Activations