© 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. 8336
    Prev
    Next
    INDEX
    Explanations

    country names and abbreviations

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

    helpline contact information

    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
     generically
    0.38
     Хо
    0.33
     pach
    0.32
     morphologies
    0.32
     e
    0.32
     dichotom
    0.32
     casework
    0.32
     যেমন
    0.31
    ់
    0.31
     ${\
    0.30
    POSITIVE LOGITS
    iya
    0.37
    东
    0.36
    धारी
    0.33
    இந்த
    0.33
    आई
    0.32
    ئة
    0.32
    这是
    0.32
     मेंबर
    0.32
    זה
    0.32
    𝑈
    0.31
    Activations Density 0.055%

    No Known Activations