© 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. 18067
    Prev
    Next
    INDEX
    Explanations

    stay followed by continuation

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

    staying in a state

    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
    2
    0.63
    ה
    0.55
    他
    0.55
    ן
    0.55
    שת
    0.53
    يمق
    0.53
    ترى
    0.53
    ל
    0.53
    म्बर
    0.52
     naar
    0.52
    POSITIVE LOGITS
     stays
    0.97
    stays
    0.95
     stayed
    0.89
     STAY
    0.87
     stay
    0.82
    stay
    0.80
     atentos
    0.72
     Stay
    0.71
    Stay
    0.66
     dłu
    0.64
    Activations Density 0.055%

    No Known Activations