© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 82720
    Prev
    Next
    INDEX
    Explanations

    want followed by pronoun or to

    np_acts-logits-general · gemini-2.5-flash-lite

    want to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     despi
    0.37
     demanded
    0.35
     vreau
    0.35
     tormented
    0.35
     insisted
    0.34
     humiliated
    0.34
    цкі
    0.34
    ኀ
    0.34
    دی
    0.33
     shouted
    0.32
    POSITIVE LOGITS
    ES
    0.36
    ーン
    0.33
     गार्डन
    0.33
     tros
    0.33
     Fallon
    0.32
    recipient
    0.32
    EC
    0.32
     حص
    0.31
    initialized
    0.31
    ູນ
    0.31
    Activations Density 0.025%

    No Known Activations