© 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. 217464
    Prev
    Next
    INDEX
    Explanations

    actions followed by movement or completion

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

    actions leading to conclusions

    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
     the
    0.38
    ла
    0.38
    ле
    0.31
    вала
    0.29
     “
    0.29
    пе
    0.29
     his
    0.28
    ва
    0.28
     все
    0.28
    ↵
    0.27
    POSITIVE LOGITS
     जेव्हा
    0.33
     هستیم
    0.31
     sofern
    0.31
     obwohl
    0.30
     هستند
    0.30
    変数
    0.30
     नकार
    0.29
    ofstream
    0.29
    regarding
    0.29
     wanneer
    0.29
    Activations Density 0.037%

    No Known Activations