© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 148200
    Prev
    Next
    INDEX
    Explanations

    want

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

    want and wanting

    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
     ağırl
    0.52
    ید
    0.52
     ওজন
    0.51
    ీ
    0.50
     weights
    0.50
    weights
    0.50
     அதிகார
    0.50
     weight
    0.49
     cerrar
    0.49
    ավ
    0.49
    POSITIVE LOGITS
     ktorí
    0.52
    ほしい
    0.45
     IN
    0.44
     potrebné
    0.43
    were
    0.42
    ಮಾಣ
    0.42
    ڍ
    0.42
    va
    0.41
    want
    0.41
    vang
    0.41
    Activations Density 0.004%

    No Known Activations