© 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. 15573
    Prev
    Next
    INDEX
    Explanations

    wanting or seeking specific things

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

    desired things or actions

    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
    េះ
    0.38
     التعامل
    0.38
    Ἑ
    0.38
    ્યારે
    0.38
     encerr
    0.37
    பொ
    0.37
    這一
    0.36
    PSW
    0.36
    について
    0.36
    })();
    0.36
    POSITIVE LOGITS
     desired
    2.16
    desired
    1.92
     원하는
    1.91
     gewüns
    1.87
    Desired
    1.63
     ønsk
    1.62
    想要的
    1.53
     desej
    1.48
     istedi
    1.42
     wanted
    1.40
    Activations Density 0.128%

    No Known Activations