© 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. 38487
    Prev
    Next
    INDEX
    Explanations

    military or has been

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

    mapping terrain

    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
     наиболь
    0.49
    habitude
    0.46
    𝒓
    0.45
    लब्
    0.43
    érature
    0.43
    ्यूटर
    0.42
     прошло
    0.41
     चली
    0.41
     perto
    0.40
     περισσότε
    0.40
    POSITIVE LOGITS
    CLIENT
    0.51
    島
    0.50
    the
    0.48
    ITA
    0.48
    島の
    0.47
    （
    0.46
    ជន
    0.46
    ui
    0.46
     Appalach
    0.46
     islands
    0.45
    Activations Density 0.000%

    No Known Activations