© 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-16K
    7. 7396
    Prev
    Next
    INDEX
    Explanations

    want to express a need or desire

    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
     a
    1.13
     an
    1.06
     sebuah
    1.06
     некоторые
    1.06
     cortos
    1.06
     exces
    1.05
     कोई
    1.01
     suatu
    1.01
     celular
    1.00
     ein
    0.98
    POSITIVE LOGITS
    SHE
    1.05
    YOU
    1.00
    H
    0.98
    OR
    0.95
    ંગી
    0.94
    Е
    0.93
    K
    0.91
    Evaluate
    0.89
    IN
    0.88
    BODY
    0.88
    Activations Density 0.250%

    No Known Activations