© 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. 188159
    Prev
    Next
    INDEX
    Explanations

    adjective + noun (place, person, concept)

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

    have a, the movies, from small, be stacked

    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
     Новости
    0.51
     Password
    0.50
    Password
    0.49
    }^
    0.48
     Respons
    0.47
    Config
    0.46
     PASSWORD
    0.46
     Dosage
    0.46
     இரண்ட
    0.45
     Experiences
    0.45
    POSITIVE LOGITS
    n
    0.53
    лые
    0.52
     algún
    0.50
     intrusions
    0.50
    ائل
    0.50
     intrusion
    0.49
    government
    0.49
     ferrugine
    0.48
    mäßig
    0.47
    gouv
    0.47
    Activations Density 0.000%

    No Known Activations