© 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. 163898
    Prev
    Next
    INDEX
    Explanations

    force

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

    forcing actions

    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
    utiliser
    0.53
    굶
    0.53
    effic
    0.52
    residents
    0.49
    intérieur
    0.48
    inflammation
    0.48
    ouvrir
    0.47
    Residents
    0.46
    잉
    0.45
    responding
    0.45
    POSITIVE LOGITS
     symmetric
    0.49
     idx
    0.48
     nucleon
    0.48
     s
    0.47
     dyes
    0.47
     cặp
    0.46
     miền
    0.45
     định
    0.45
     t
    0.45
     Low
    0.45
    Activations Density 0.001%

    No Known Activations