© 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. 111149
    Prev
    Next
    INDEX
    Explanations

    regarded as, followed by

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

    Sky, Windows, Bing, Pinterest, Server

    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
     harem
    0.47
    ‍♀️
    0.47
     covalent
    0.45
    bromo
    0.44
    accam
    0.44
    မျ
    0.43
     sinh
    0.43
     સમયે
    0.43
     prezzo
    0.42
    asshi
    0.42
    POSITIVE LOGITS
     geändert
    0.44
     needless
    0.41
     Supplied
    0.41
    }$\
    0.40
    Gesch
    0.40
     Decide
    0.40
     Başkanı
    0.40
     MessageBox
    0.39
     комнаты
    0.38
    ಧಾನ
    0.38
    Activations Density 0.001%

    No Known Activations