© 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. 126407
    Prev
    Next
    INDEX
    Explanations

    investment, exam, only, in

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

    adjectives followed by related nouns

    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
    atis
    0.52
    ✡
    0.50
    ים
    0.47
    oter
    0.47
    </strong>
    0.47
    ates
    0.46
    ્સ
    0.46
    ats
    0.46
    ่
    0.45
    īn
    0.45
    POSITIVE LOGITS
     cuerpos
    0.53
     teníamos
    0.53
     revert
    0.51
     emocional
    0.49
     compi
    0.48
     misdemeanor
    0.47
     formalized
    0.47
     lacer
    0.47
     reverting
    0.47
     sujeito
    0.46
    Activations Density 0.000%

    No Known Activations