© 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. 210872
    Prev
    Next
    INDEX
    Explanations

    distinct z, investigative, religion, withdraw

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

    medical developments

    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
    АР
    0.49
    Ци
    0.48
    帝
    0.48
    記
    0.47
    АС
    0.47
    希
    0.46
    柑
    0.46
    АТ
    0.46
    里
    0.45
    マル
    0.45
    POSITIVE LOGITS
     Bathroom
    0.55
     Util
    0.50
     Coupling
    0.50
     Girls
    0.49
     Allow
    0.49
     Reliability
    0.49
    ꗥ
    0.47
     Waterproof
    0.47
     Propulsion
    0.47
     Formulation
    0.47
    Activations Density 0.002%

    No Known Activations