© 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. 163250
    Prev
    Next
    INDEX
    Explanations

    providing construction

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

    explaining concepts and definitions

    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
     internet
    0.61
     Internet
    0.55
     easiest
    0.52
     opponents
    0.48
    m
    0.48
     enemies
    0.45
     market
    0.45
     people
    0.44
     Business
    0.44
     Money
    0.44
    POSITIVE LOGITS
    ப்பழ
    0.50
     слоя
    0.49
    писа
    0.47
     치료
    0.47
    鳟
    0.47
     поколения
    0.45
    снов
    0.45
    ἕ
    0.45
     شناخته
    0.44
    cultured
    0.44
    Activations Density 0.000%

    No Known Activations