© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-16K
    7. 14209
    Prev
    Next
    INDEX
    Explanations

    for or to followed by a noun/verb

    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
     Portanto
    1.16
    ين
    1.09
    oretically
    1.07
     U
    0.97
     rappel
    0.97
    Pregnant
    0.96
     Sedangkan
    0.91
     PB
    0.90
    ించాలి
    0.89
     B
    0.89
    POSITIVE LOGITS
    _
    1.11
    aal
    1.09
    الف
    1.07
    aus
    1.04
    ことです
    1.01
    clude
    0.93
    ﺽ
    0.93
    eers
    0.90
    𝘨
    0.90
    ্স
    0.89
    Activations Density 0.145%

    No Known Activations