© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 46988
    Prev
    Next
    INDEX
    Explanations

    you want

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

    depending on nuance and intention

    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
    Not in Any Lists

    No Comments

    Negative Logits
    נד
    0.40
    п
    0.40
    స్య
    0.39
    т
    0.39
    fet
    0.39
    መስ
    0.39
    Goss
    0.39
    ческие
    0.38
    දර
    0.38
    ブ
    0.38
    POSITIVE LOGITS
     muốn
    0.84
     want
    0.83
     wanting
    0.74
    只想
    0.72
     Want
    0.68
    不想
    0.68
     хотим
    0.65
     ingin
    0.64
    want
    0.64
     queremos
    0.64
    Activations Density 0.103%

    No Known Activations