© 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. 117584
    Prev
    Next
    INDEX
    Explanations

    varied nouns and actions

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

    Restoration, power, allies, vanished

    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
     Çocuk
    0.49
    Children
    0.47
    儿童
    0.47
    اری
    0.45
    බන්ධ
    0.45
    actéristiques
    0.44
    бовать
    0.44
    닌
    0.44
    aç
    0.43
     বৈশিষ্ট
    0.43
    POSITIVE LOGITS
     कर्ज
    0.44
     প্রায়
    0.42
     sider
    0.42
    steel
    0.42
     ponytail
    0.42
     वित्त
    0.40
     bracelet
    0.40
     deceased
    0.39
     कसा
    0.39
     chieftain
    0.39
    Activations Density 0.000%

    No Known Activations